refactor: orchestrator-driven reconciliation and structured agent returns
Phase 1: Fix Story Reconciliation - Remove Reconciler agent (orchestrator does this directly now) - Rewrite step-4.5 from XML to explicit Bash/Read/Edit commands - Update batch-super-dev instructions with explicit tool calls - Principle: agents do creative work, orchestrator does bookkeeping Phase 2: Structured Agent Returns - Add ## AGENT COMPLETE format to builder, inspector, reviewer, fixer - Remove story/sprint update responsibility from Fixer agent - Agents now return parseable output (files, status, evidence) This aligns BMAD workflows with GSD patterns for better reliability.
This commit is contained in:
Jonah Schulte
parent
e1c6a05259
commit
07592e4c36
|
|
@ -895,11 +895,20 @@ Enter number (2-10) or 'all':
|
|||
<check if="super-dev-pipeline succeeded">
|
||||
<output>✅ Implementation complete: {{story_key}}</output>
|
||||
|
||||
<action>Execute Step 4.5: Smart Story Reconciliation</action>
|
||||
<action>Load reconciliation instructions: {installed_path}/step-4.5-reconcile-story-status.md</action>
|
||||
<action>Execute reconciliation with story_key={{story_key}}</action>
|
||||
<critical>ORCHESTRATOR: You must execute reconciliation directly using Bash/Read/Edit tools.</critical>
|
||||
<critical>Do NOT delegate this to an agent. YOU do it.</critical>
|
||||
|
||||
<check if="reconciliation succeeded">
|
||||
<reconciliation>
|
||||
1. Use Bash: `git log -3 --oneline | grep "{{story_key}}"` to find commit
|
||||
2. Use Bash: `git diff HEAD~1 --name-only` to get files changed
|
||||
3. Use Read: `docs/sprint-artifacts/{{story_key}}.md` to see tasks
|
||||
4. Use Edit: Check off tasks (change `- [ ]` to `- [x]`) for completed work
|
||||
5. Use Edit: Fill Dev Agent Record with files/date/summary
|
||||
6. Use Bash: Verify with `grep -c "^- \[x\]"` (must be > 0)
|
||||
7. Use Edit: Update sprint-status.yaml to "done" or "review"
|
||||
</reconciliation>
|
||||
|
||||
<check if="reconciliation succeeded (checked tasks > 0)">
|
||||
<output>✅ COMPLETED: {{story_key}} (reconciled)</output>
|
||||
<action>Increment completed counter</action>
|
||||
|
||||
|
|
@ -1096,16 +1105,24 @@ Press [C] to continue or [P] to pause:
|
|||
|
||||
<output>✅ Worker {{worker_id}} completed: {{story_key}}</output>
|
||||
|
||||
<action>Execute Step 4.5: Smart Story Reconciliation</action>
|
||||
<action>Load reconciliation instructions: {installed_path}/step-4.5-reconcile-story-status.md</action>
|
||||
<action>Execute reconciliation with story_key={{story_key}}</action>
|
||||
<critical>ORCHESTRATOR: You must execute reconciliation directly using Bash/Read/Edit tools.</critical>
|
||||
|
||||
<check if="reconciliation succeeded">
|
||||
<reconciliation>
|
||||
1. Use Bash: `git log -3 --oneline | grep "{{story_key}}"` to find commit
|
||||
2. Use Bash: `git diff HEAD~1 --name-only` to get files changed
|
||||
3. Use Read: `docs/sprint-artifacts/{{story_key}}.md` to see tasks
|
||||
4. Use Edit: Check off tasks (change `- [ ]` to `- [x]`) for completed work
|
||||
5. Use Edit: Fill Dev Agent Record with files/date/summary
|
||||
6. Use Bash: Verify with `grep -c "^- \[x\]"` (must be > 0)
|
||||
7. Use Edit: Update sprint-status.yaml to "done" or "review"
|
||||
</reconciliation>
|
||||
|
||||
<check if="reconciliation succeeded (checked tasks > 0)">
|
||||
<output>✅ COMPLETED: {{story_key}} (reconciled)</output>
|
||||
<action>Add to completed_stories</action>
|
||||
</check>
|
||||
|
||||
<check if="reconciliation failed">
|
||||
<check if="reconciliation failed (checked tasks = 0)">
|
||||
<output>⚠️ WARNING: {{story_key}} completed but reconciliation failed</output>
|
||||
<action>Add to completed_stories (implementation successful)</action>
|
||||
<action>Add to reconciliation_warnings: {story_key: {{story_key}}, warning_message: "Reconciliation failed - manual verification needed"}</action>
|
||||
|
|
|
|||
|
|
@ -1,390 +1,171 @@
|
|||
# Step 4.5: Smart Story Reconciliation
|
||||
# Step 4.5: Story Reconciliation (Orchestrator-Driven)
|
||||
|
||||
<critical>Execute AFTER super-dev-pipeline completes but BEFORE marking story as "completed"</critical>
|
||||
<critical>This ensures story checkboxes and status accurately reflect actual implementation</critical>
|
||||
|
||||
## Goal
|
||||
|
||||
Verify story file accuracy by reconciling:
|
||||
1. **Acceptance Criteria checkboxes** vs Dev Agent Record
|
||||
2. **Tasks/Subtasks checkboxes** vs Dev Agent Record
|
||||
3. **Definition of Done checkboxes** vs Dev Agent Record
|
||||
4. **Story status** (should be "done" if implementation complete)
|
||||
5. **sprint-status.yaml entry** (should match story file status)
|
||||
**Version:** 2.1.0
|
||||
**Execute:** AFTER super-dev-pipeline completes, BEFORE marking story done
|
||||
**Who:** Orchestrator (YOU) - not an agent
|
||||
|
||||
---
|
||||
|
||||
## Execution
|
||||
## Why Orchestrator Does This
|
||||
|
||||
### 1. Load Story File
|
||||
|
||||
<action>Read story file: {story_file_path}</action>
|
||||
<action>Extract sections:
|
||||
- Acceptance Criteria (## Acceptance Criteria)
|
||||
- Tasks / Subtasks (## Tasks / Subtasks)
|
||||
- Definition of Done (## Definition of Done)
|
||||
- Dev Agent Record (## Dev Agent Record)
|
||||
- Story status header (**Status:** ...)
|
||||
</action>
|
||||
|
||||
### 2. Analyze Dev Agent Record
|
||||
|
||||
<action>Read "Dev Agent Record" section</action>
|
||||
|
||||
<check if="Dev Agent Record is empty or says '(To be filled by dev agent)'">
|
||||
<output>⚠️ Story {{story_key}}: Dev Agent Record is empty - cannot reconcile</output>
|
||||
<output>This suggests super-dev-pipeline did not complete successfully.</output>
|
||||
<action>Mark story as FAILED reconciliation</action>
|
||||
<action>Return early (skip remaining checks)</action>
|
||||
</check>
|
||||
|
||||
<action>Parse Dev Agent Record fields:
|
||||
- **Agent Model Used** (should have model name, not empty)
|
||||
- **Implementation Summary** (should describe what was built)
|
||||
- **File List** (should list new/modified files)
|
||||
- **Test Results** (should show test counts)
|
||||
- **Completion Notes** (should document what works)
|
||||
</action>
|
||||
|
||||
<check if="Implementation Summary contains 'COMPLETE' or lists specific deliverables">
|
||||
<action>Set implementation_status = COMPLETE</action>
|
||||
</check>
|
||||
|
||||
<check if="Implementation Summary is vague or says 'pending'">
|
||||
<action>Set implementation_status = INCOMPLETE</action>
|
||||
<output>⚠️ Story {{story_key}}: Implementation appears incomplete based on Dev Agent Record</output>
|
||||
</check>
|
||||
|
||||
### 3. Reconcile Acceptance Criteria
|
||||
|
||||
<action>For each AC subsection (AC1, AC2, AC3, AC4, etc.):</action>
|
||||
|
||||
<iterate>For each checkbox in AC section:</iterate>
|
||||
|
||||
<substep n="3a" title="Identify expected status from Dev Agent Record">
|
||||
<action>Search Implementation Summary and File List for keywords from checkbox text</action>
|
||||
|
||||
<example>
|
||||
Checkbox: "[ ] FlexibleGridSection component (renders dynamic grid layouts)"
|
||||
Implementation Summary mentions: "FlexibleGridSection component created"
|
||||
File List includes: "FlexibleGridSection.tsx"
|
||||
→ Expected status: CHECKED
|
||||
</example>
|
||||
|
||||
<action>Determine expected_checkbox_status:
|
||||
- CHECKED if Implementation Summary confirms it OR File List shows created files OR Test Results mention it
|
||||
- UNCHECKED if no evidence in Dev Agent Record
|
||||
- PARTIAL if mentioned as "pending" or "infrastructure ready"
|
||||
</action>
|
||||
</substep>
|
||||
|
||||
<substep n="3b" title="Compare actual vs expected">
|
||||
<action>Read actual checkbox state from story file ([x] vs [ ] vs [~])</action>
|
||||
|
||||
<check if="actual != expected">
|
||||
<output>🔧 Reconciling AC: "{{checkbox_text}}"
|
||||
Actual: {{actual_status}}
|
||||
Expected: {{expected_status}}
|
||||
Reason: {{evidence_from_dev_record}}
|
||||
</output>
|
||||
<action>Add to reconciliation_changes list</action>
|
||||
</check>
|
||||
</substep>
|
||||
|
||||
<action>After checking all ACs:
|
||||
- Count total AC items
|
||||
- Count checked AC items (after reconciliation)
|
||||
- Calculate AC completion percentage
|
||||
</action>
|
||||
|
||||
### 4. Reconcile Tasks / Subtasks
|
||||
|
||||
<action>For each Task (Task 1, Task 2, etc.):</action>
|
||||
|
||||
<iterate>For each checkbox in Tasks section:</iterate>
|
||||
|
||||
<substep n="4a" title="Identify expected status from Dev Agent Record">
|
||||
<action>Search Implementation Summary and File List for task keywords</action>
|
||||
|
||||
<example>
|
||||
Task checkbox: "[ ] **2.2:** Create FlexibleGridSection component"
|
||||
File List includes: "apps/frontend/web/src/components/FlexibleGridSection.tsx"
|
||||
→ Expected status: CHECKED
|
||||
</example>
|
||||
|
||||
<action>Determine expected_checkbox_status using same logic as AC section</action>
|
||||
</substep>
|
||||
|
||||
<substep n="4b" title="Compare and reconcile">
|
||||
<action>Read actual checkbox state</action>
|
||||
|
||||
<check if="actual != expected">
|
||||
<output>🔧 Reconciling Task: "{{task_text}}"
|
||||
Actual: {{actual_status}}
|
||||
Expected: {{expected_status}}
|
||||
Reason: {{evidence_from_dev_record}}
|
||||
</output>
|
||||
<action>Add to reconciliation_changes list</action>
|
||||
</check>
|
||||
</substep>
|
||||
|
||||
<action>After checking all Tasks:
|
||||
- Count total task items
|
||||
- Count checked task items (after reconciliation)
|
||||
- Calculate task completion percentage
|
||||
</action>
|
||||
|
||||
### 5. Reconcile Definition of Done
|
||||
|
||||
<action>For each DoD category (Code Quality, Testing, Security, etc.):</action>
|
||||
|
||||
<iterate>For each checkbox in DoD section:</iterate>
|
||||
|
||||
<substep n="5a" title="Determine expected status">
|
||||
<action>Check Test Results, Completion Notes for evidence</action>
|
||||
|
||||
<example>
|
||||
DoD checkbox: "[ ] Type check passes: `pnpm type-check` (zero errors)"
|
||||
Completion Notes say: "Type check passes ✅"
|
||||
→ Expected status: CHECKED
|
||||
</example>
|
||||
|
||||
<example>
|
||||
DoD checkbox: "[ ] Unit tests: 90%+ coverage"
|
||||
Test Results say: "37 tests passing"
|
||||
Completion Notes say: "100% coverage on FlexibleGridSection"
|
||||
→ Expected status: CHECKED
|
||||
</example>
|
||||
|
||||
<action>Determine expected_checkbox_status</action>
|
||||
</substep>
|
||||
|
||||
<substep n="5b" title="Compare and reconcile">
|
||||
<action>Read actual checkbox state</action>
|
||||
|
||||
<check if="actual != expected">
|
||||
<output>🔧 Reconciling DoD: "{{dod_text}}"
|
||||
Actual: {{actual_status}}
|
||||
Expected: {{expected_status}}
|
||||
Reason: {{evidence_from_dev_record}}
|
||||
</output>
|
||||
<action>Add to reconciliation_changes list</action>
|
||||
</check>
|
||||
</substep>
|
||||
|
||||
<action>After checking all DoD items:
|
||||
- Count total DoD items
|
||||
- Count checked DoD items (after reconciliation)
|
||||
- Calculate DoD completion percentage
|
||||
</action>
|
||||
|
||||
### 6. Determine Correct Story Status
|
||||
|
||||
<action>Based on completion percentages, determine correct story status:</action>
|
||||
|
||||
<check if="AC >= 95% AND Tasks >= 95% AND DoD >= 95%">
|
||||
<action>Set correct_story_status = "done"</action>
|
||||
</check>
|
||||
|
||||
<check if="AC >= 80% AND Tasks >= 80% AND DoD >= 80%">
|
||||
<action>Set correct_story_status = "review"</action>
|
||||
</check>
|
||||
|
||||
<check if="AC < 80% OR Tasks < 80% OR DoD < 80%">
|
||||
<action>Set correct_story_status = "in-progress"</action>
|
||||
</check>
|
||||
|
||||
<check if="implementation_status == INCOMPLETE">
|
||||
<action>Override: Set correct_story_status = "in-progress"</action>
|
||||
<output>⚠️ Overriding status to "in-progress" due to incomplete implementation</output>
|
||||
</check>
|
||||
|
||||
<action>Read current story status from story file (**Status:** ...)</action>
|
||||
|
||||
<check if="current_story_status != correct_story_status">
|
||||
<output>🔧 Story status mismatch:
|
||||
Current: {{current_story_status}}
|
||||
Expected: {{correct_story_status}}
|
||||
Reason: AC={{ac_pct}}% Tasks={{tasks_pct}}% DoD={{dod_pct}}%
|
||||
</output>
|
||||
<action>Add to reconciliation_changes list</action>
|
||||
</check>
|
||||
|
||||
### 7. Verify sprint-status.yaml Entry
|
||||
|
||||
<action>Read {sprint_status} file</action>
|
||||
<action>Find entry for {{story_key}}</action>
|
||||
<action>Extract current status from sprint-status.yaml</action>
|
||||
|
||||
<check if="sprint_status_yaml_status != correct_story_status">
|
||||
<output>🔧 sprint-status.yaml mismatch:
|
||||
Current: {{sprint_status_yaml_status}}
|
||||
Expected: {{correct_story_status}}
|
||||
</output>
|
||||
<action>Add to reconciliation_changes list</action>
|
||||
</check>
|
||||
|
||||
### 8. Apply Reconciliation Changes
|
||||
|
||||
<check if="reconciliation_changes is empty">
|
||||
<output>✅ Story {{story_key}}: Already accurate (0 changes needed)</output>
|
||||
<action>Return SUCCESS (no updates needed)</action>
|
||||
</check>
|
||||
|
||||
<check if="reconciliation_changes is NOT empty">
|
||||
<output>
|
||||
🔧 Story {{story_key}}: Reconciling {{count}} issues
|
||||
|
||||
**Changes to apply:**
|
||||
{{#each reconciliation_changes}}
|
||||
{{@index}}. {{change_description}}
|
||||
{{/each}}
|
||||
</output>
|
||||
|
||||
<ask>Apply these reconciliation changes? (yes/no):</ask>
|
||||
|
||||
<check if="response != 'yes'">
|
||||
<output>⏭️ Skipping reconciliation for {{story_key}}</output>
|
||||
<action>Return SUCCESS (user declined changes)</action>
|
||||
</check>
|
||||
|
||||
<substep n="8a" title="Update Acceptance Criteria">
|
||||
<action>For each AC checkbox that needs updating:</action>
|
||||
<action>Use Edit tool to update checkbox from [ ] to [x] or [~]</action>
|
||||
<action>Add note explaining why: "- [x] Item - COMPLETE: {{evidence}}"</action>
|
||||
</substep>
|
||||
|
||||
<substep n="8b" title="Update Tasks / Subtasks">
|
||||
<action>For each Task checkbox that needs updating:</action>
|
||||
<action>Use Edit tool to update checkbox</action>
|
||||
<action>Update task header if all subtasks complete: "### Task 1: ... ✅ COMPLETE"</action>
|
||||
</substep>
|
||||
|
||||
<substep n="8c" title="Update Definition of Done">
|
||||
<action>For each DoD checkbox that needs updating:</action>
|
||||
<action>Use Edit tool to update checkbox</action>
|
||||
<action>Add verification note: "- [x] Item ✅ (verified in Dev Agent Record)"</action>
|
||||
</substep>
|
||||
|
||||
<substep n="8d" title="Update Story Status">
|
||||
<check if="story status needs updating">
|
||||
<action>Use Edit tool to update status line</action>
|
||||
<action>Change from: **Status:** {{old_status}}</action>
|
||||
<action>Change to: **Status:** {{correct_story_status}}</action>
|
||||
</check>
|
||||
</substep>
|
||||
|
||||
<substep n="8e" title="Update sprint-status.yaml with status and progress">
|
||||
<check if="sprint-status.yaml needs updating">
|
||||
<action>Use Edit tool to update status entry</action>
|
||||
|
||||
<action>Count tasks from story file:
|
||||
- total_tasks = all top-level tasks
|
||||
- checked_tasks = tasks marked [x]
|
||||
- progress_pct = (checked_tasks / total_tasks) × 100
|
||||
</action>
|
||||
|
||||
<action>Update comment with progress tracking (NEW v1.3.0):
|
||||
If status == "in-progress":
|
||||
Format: {{story_key}}: in-progress # {{checked_tasks}}/{{total_tasks}} tasks ({{progress_pct}}%)
|
||||
|
||||
If status == "review":
|
||||
Format: {{story_key}}: review # {{checked_tasks}}/{{total_tasks}} tasks ({{progress_pct}}%) - awaiting review
|
||||
|
||||
If status == "done":
|
||||
Format: {{story_key}}: done # ✅ COMPLETED: {{brief_summary}}
|
||||
</action>
|
||||
|
||||
<example>
|
||||
Before: 20-8-...: ready-for-dev # Story description
|
||||
During: 20-8-...: in-progress # 3/10 tasks (30%)
|
||||
During: 20-8-...: in-progress # 7/10 tasks (70%)
|
||||
Review: 20-8-...: review # 10/10 tasks (100%) - awaiting review
|
||||
After: 20-8-...: done # ✅ COMPLETED: Component + tests + docs
|
||||
</example>
|
||||
</check>
|
||||
</substep>
|
||||
|
||||
<output>✅ Story {{story_key}}: Reconciliation complete ({{count}} changes applied)</output>
|
||||
</check>
|
||||
|
||||
### 9. Final Verification
|
||||
|
||||
<action>Re-read story file to verify changes applied correctly</action>
|
||||
<action>Calculate final completion percentages</action>
|
||||
|
||||
<output>
|
||||
📊 Story {{story_key}} - Final Status
|
||||
|
||||
**Acceptance Criteria:** {{ac_checked}}/{{ac_total}} ({{ac_pct}}%)
|
||||
**Tasks/Subtasks:** {{tasks_checked}}/{{tasks_total}} ({{tasks_pct}}%)
|
||||
**Definition of Done:** {{dod_checked}}/{{dod_total}} ({{dod_pct}}%)
|
||||
|
||||
**Story Status:** {{correct_story_status}}
|
||||
**sprint-status.yaml:** {{correct_story_status}}
|
||||
|
||||
{{#if correct_story_status == "done"}}
|
||||
✅ Story is COMPLETE and accurately reflects implementation
|
||||
{{/if}}
|
||||
|
||||
{{#if correct_story_status == "review"}}
|
||||
⚠️ Story needs review (some items incomplete)
|
||||
{{/if}}
|
||||
|
||||
{{#if correct_story_status == "in-progress"}}
|
||||
⚠️ Story has significant gaps (implementation incomplete)
|
||||
{{/if}}
|
||||
</output>
|
||||
|
||||
<action>Return SUCCESS with reconciliation summary</action>
|
||||
Agents ignore reconciliation instructions. The orchestrator:
|
||||
- Has full context of what just happened
|
||||
- Can use tools directly (Bash, Read, Edit)
|
||||
- Won't skip "boring" bookkeeping tasks
|
||||
|
||||
---
|
||||
|
||||
## Success Criteria
|
||||
## Execute These Steps
|
||||
|
||||
Story reconciliation succeeds when:
|
||||
1. ✅ All checkboxes match Dev Agent Record evidence
|
||||
2. ✅ Story status accurately reflects completion (done/review/in-progress)
|
||||
3. ✅ sprint-status.yaml entry matches story file status
|
||||
4. ✅ Completion percentages calculated and reported
|
||||
5. ✅ Changes documented in reconciliation summary
|
||||
### Step 1: Get What Was Built
|
||||
|
||||
---
|
||||
Run this command with Bash tool:
|
||||
|
||||
## Error Handling
|
||||
```bash
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "🔧 STORY RECONCILIATION: {{story_key}}"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
<check if="story file not found">
|
||||
<output>❌ Story {{story_key}}: File not found at {{story_file_path}}</output>
|
||||
<action>Return FAILED reconciliation</action>
|
||||
</check>
|
||||
# Get the commit for this story
|
||||
echo "Recent commits:"
|
||||
git log -5 --oneline | grep -i "{{story_key}}" || echo "(no commits found with story key)"
|
||||
|
||||
<check if="Dev Agent Record missing or empty">
|
||||
<output>⚠️ Story {{story_key}}: Cannot reconcile - Dev Agent Record not populated</output>
|
||||
<action>Mark as INCOMPLETE (not implemented yet)</action>
|
||||
<action>Return WARNING reconciliation</action>
|
||||
</check>
|
||||
|
||||
<check if="Edit tool fails">
|
||||
<output>❌ Story {{story_key}}: Failed to apply changes (Edit tool error)</output>
|
||||
<action>Log error details</action>
|
||||
<action>Return FAILED reconciliation</action>
|
||||
</check>
|
||||
|
||||
---
|
||||
|
||||
## Integration with batch-super-dev
|
||||
|
||||
**Insert this step:**
|
||||
- **Sequential mode:** After Step 4s-a (Process individual story), before marking completed
|
||||
- **Parallel mode:** After Step 4p-a (Spawn Task agents), after agent completes but before marking completed
|
||||
|
||||
**Flow:**
|
||||
```
|
||||
super-dev-pipeline completes → Step 4.5 (Reconcile) → Mark as completed/failed
|
||||
# Get files changed
|
||||
echo ""
|
||||
echo "Files changed in last commit:"
|
||||
git diff HEAD~1 --name-only | grep -v "__tests__" | grep -v "\.test\." | head -20
|
||||
```
|
||||
|
||||
**Benefits:**
|
||||
- Ensures all batch-processed stories have accurate status
|
||||
- Catches mismatches automatically
|
||||
- Prevents "done" stories with unchecked items
|
||||
- Maintains sprint-status.yaml accuracy
|
||||
Store the output - you'll need it for the next steps.
|
||||
|
||||
### Step 2: Read Story File
|
||||
|
||||
Use Read tool on: `docs/sprint-artifacts/{{story_key}}.md`
|
||||
|
||||
Find these sections:
|
||||
- **Tasks** (lines starting with `- [ ]` or `- [x]`)
|
||||
- **Dev Agent Record** (section with Agent Model, Implementation Date, etc.)
|
||||
|
||||
### Step 3: Check Off Completed Tasks
|
||||
|
||||
For EACH task in the Tasks section that relates to files changed:
|
||||
|
||||
Use Edit tool:
|
||||
```
|
||||
file_path: docs/sprint-artifacts/{{story_key}}.md
|
||||
old_string: "- [ ] Create the SomeComponent"
|
||||
new_string: "- [x] Create the SomeComponent"
|
||||
```
|
||||
|
||||
**Match logic:**
|
||||
- If task mentions a file that was created → check it off
|
||||
- If task mentions a service/component that now exists → check it off
|
||||
- If unsure → leave unchecked (don't over-claim)
|
||||
|
||||
### Step 4: Fill Dev Agent Record
|
||||
|
||||
Use Edit tool to replace the placeholder record:
|
||||
|
||||
```
|
||||
file_path: docs/sprint-artifacts/{{story_key}}.md
|
||||
old_string: "### Dev Agent Record
|
||||
- **Agent Model Used:** [Not set]
|
||||
- **Implementation Date:** [Not set]
|
||||
- **Files Created/Modified:** [Not set]
|
||||
- **Tests Added:** [Not set]
|
||||
- **Completion Notes:** [Not set]"
|
||||
new_string: "### Dev Agent Record
|
||||
- **Agent Model Used:** Claude Sonnet 4 (multi-agent pipeline)
|
||||
- **Implementation Date:** 2026-01-26
|
||||
- **Files Created/Modified:**
|
||||
- path/to/file1.ts
|
||||
- path/to/file2.ts
|
||||
[list all files from git diff]
|
||||
- **Tests Added:** X tests (from Inspector report)
|
||||
- **Completion Notes:** Implemented [brief summary]"
|
||||
```
|
||||
|
||||
### Step 5: Verify Updates
|
||||
|
||||
Run this command with Bash tool:
|
||||
|
||||
```bash
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "🔍 RECONCILIATION VERIFICATION"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
STORY_FILE="docs/sprint-artifacts/{{story_key}}.md"
|
||||
|
||||
# Count checked tasks
|
||||
CHECKED=$(grep -c "^- \[x\]" "$STORY_FILE" 2>/dev/null || echo "0")
|
||||
UNCHECKED=$(grep -c "^- \[ \]" "$STORY_FILE" 2>/dev/null || echo "0")
|
||||
TOTAL=$((CHECKED + UNCHECKED))
|
||||
echo "Tasks: $CHECKED/$TOTAL checked"
|
||||
|
||||
if [ "$CHECKED" -eq 0 ]; then
|
||||
echo ""
|
||||
echo "❌ BLOCKER: Zero tasks checked off"
|
||||
echo "You MUST go back to Step 3 and check off tasks"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Check Dev Agent Record filled
|
||||
if grep -q "Implementation Date: \[Not set\]" "$STORY_FILE" 2>/dev/null; then
|
||||
echo "❌ BLOCKER: Dev Agent Record not filled"
|
||||
echo "You MUST go back to Step 4 and fill it"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if grep -A 3 "### Dev Agent Record" "$STORY_FILE" | grep -q "Implementation Date: 202"; then
|
||||
echo "✅ Dev Agent Record: Filled"
|
||||
else
|
||||
echo "❌ BLOCKER: Dev Agent Record incomplete"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo ""
|
||||
echo "✅ RECONCILIATION COMPLETE"
|
||||
echo " Checked tasks: $CHECKED/$TOTAL"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
```
|
||||
|
||||
### Step 6: Update Sprint Status
|
||||
|
||||
Use Read tool: `docs/sprint-artifacts/sprint-status.yaml`
|
||||
|
||||
Find the entry for {{story_key}} and use Edit tool to update:
|
||||
|
||||
```
|
||||
old_string: "{{story_key}}: ready-for-dev"
|
||||
new_string: "{{story_key}}: done # ✅ COMPLETED 2026-01-26"
|
||||
```
|
||||
|
||||
Or if 95%+ complete but not 100%:
|
||||
```
|
||||
new_string: "{{story_key}}: review # 8/10 tasks - awaiting review"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Status Decision Logic
|
||||
|
||||
Based on verification results:
|
||||
|
||||
| Condition | Status |
|
||||
|-----------|--------|
|
||||
| 95%+ tasks checked + Dev Record filled | `done` |
|
||||
| 80-94% tasks checked | `review` |
|
||||
| <80% tasks checked | `in-progress` |
|
||||
| Dev Record not filled | `in-progress` |
|
||||
|
||||
---
|
||||
|
||||
## If Verification Fails
|
||||
|
||||
1. **DO NOT** proceed to next story
|
||||
2. **DO NOT** mark story as done
|
||||
3. **FIX** the issue using Edit tool
|
||||
4. **RE-RUN** verification command
|
||||
5. **REPEAT** until verification passes
|
||||
|
||||
This is mandatory. No shortcuts.
|
||||
|
|
|
|||
|
|
@ -93,4 +93,43 @@ When complete, provide:
|
|||
|
||||
---
|
||||
|
||||
## When Complete, Return This Format
|
||||
|
||||
```markdown
|
||||
## AGENT COMPLETE
|
||||
|
||||
**Agent:** builder
|
||||
**Story:** {{story_key}}
|
||||
**Status:** SUCCESS | FAILED
|
||||
|
||||
### Files Created
|
||||
- path/to/new/file1.ts
|
||||
- path/to/new/file2.ts
|
||||
|
||||
### Files Modified
|
||||
- path/to/existing/file.ts
|
||||
|
||||
### Tests Added
|
||||
- X test files
|
||||
- Y test cases total
|
||||
|
||||
### Implementation Summary
|
||||
Brief description of what was built and key decisions made.
|
||||
|
||||
### Known Gaps
|
||||
- Any functionality not implemented
|
||||
- Any edge cases not handled
|
||||
- NONE if all tasks complete
|
||||
|
||||
### Ready For
|
||||
Inspector validation (next phase)
|
||||
```
|
||||
|
||||
**Why this format?** The orchestrator parses this output to:
|
||||
- Verify claimed files actually exist
|
||||
- Track what was built for reconciliation
|
||||
- Route to next phase appropriately
|
||||
|
||||
---
|
||||
|
||||
**Remember:** You are the BUILDER. Build it well, but don't validate or review your own work. Other agents will do that with fresh eyes.
|
||||
|
|
|
|||
|
|
@ -20,15 +20,15 @@ You are the **FIXER** agent. Your job is to fix CRITICAL and HIGH issues from th
|
|||
- Fix security vulnerabilities immediately
|
||||
- Fix logic bugs and edge cases
|
||||
- Re-run tests after each fix
|
||||
- Update story checkboxes
|
||||
- Update sprint-status.yaml
|
||||
- Commit changes
|
||||
- Commit code changes with descriptive message
|
||||
|
||||
**DO NOT:**
|
||||
- Skip CRITICAL issues
|
||||
- Skip HIGH issues
|
||||
- Spend time on LOW issues
|
||||
- Make unnecessary changes
|
||||
- Update story checkboxes (orchestrator does this)
|
||||
- Update sprint-status.yaml (orchestrator does this)
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -79,22 +79,7 @@ low_issues: [#10, #11] # SKIP (gold-plating)
|
|||
|
||||
## After Fixing Issues
|
||||
|
||||
### 1. Update Story File
|
||||
|
||||
**Mark completed tasks:**
|
||||
```bash
|
||||
# Update checkboxes in story file
|
||||
# Change [ ] to [x] for completed tasks
|
||||
```
|
||||
|
||||
### 2. Update Sprint Status
|
||||
|
||||
**Update sprint-status.yaml:**
|
||||
```yaml
|
||||
17-10-occupant-agreement-view: done # was: ready-for-dev
|
||||
```
|
||||
|
||||
### 3. Commit Changes
|
||||
### Commit Changes
|
||||
|
||||
```bash
|
||||
git add .
|
||||
|
|
@ -153,10 +138,6 @@ All tests passing, type check clean, lint clean."
|
|||
|
||||
**Git:**
|
||||
- ✅ Commit created: a1b2c3d
|
||||
- ✅ Story checkboxes updated
|
||||
- ✅ Sprint status updated
|
||||
|
||||
**Story Status:** COMPLETE
|
||||
```
|
||||
|
||||
---
|
||||
|
|
@ -183,4 +164,47 @@ All tests passing, type check clean, lint clean."
|
|||
|
||||
---
|
||||
|
||||
## When Complete, Return This Format
|
||||
|
||||
```markdown
|
||||
## AGENT COMPLETE
|
||||
|
||||
**Agent:** fixer
|
||||
**Story:** {{story_key}}
|
||||
**Status:** SUCCESS | PARTIAL | FAILED
|
||||
|
||||
### Issues Fixed
|
||||
- **CRITICAL:** X/Y fixed
|
||||
- **HIGH:** X/Y fixed
|
||||
- **Total:** X issues resolved
|
||||
|
||||
### Fixes Applied
|
||||
1. [CRITICAL] file.ts:45 - Fixed SQL injection with parameterized query
|
||||
2. [HIGH] file.ts:89 - Added null check
|
||||
|
||||
### Files Modified
|
||||
- path/to/file1.ts
|
||||
- path/to/file2.ts
|
||||
|
||||
### Quality Checks
|
||||
- **Type Check:** PASS | FAIL
|
||||
- **Lint:** PASS | FAIL
|
||||
- **Tests:** X passing, Y failing
|
||||
|
||||
### Git Commit
|
||||
- **Hash:** abc123
|
||||
- **Message:** fix({{story_key}}): address code review findings
|
||||
|
||||
### Deferred Issues
|
||||
- MEDIUM: X issues (defer to follow-up)
|
||||
- LOW: X issues (skip as gold-plating)
|
||||
|
||||
### Ready For
|
||||
Orchestrator reconciliation (story file updates)
|
||||
```
|
||||
|
||||
**Note:** Story checkboxes and sprint-status updates are done by the orchestrator, not you.
|
||||
|
||||
---
|
||||
|
||||
**Remember:** You are the FIXER. Fix real problems, skip gold-plating, commit when done.
|
||||
|
|
|
|||
|
|
@ -150,4 +150,35 @@ Cannot proceed to code review until these are fixed.
|
|||
|
||||
---
|
||||
|
||||
## When Complete, Return This Format
|
||||
|
||||
```markdown
|
||||
## AGENT COMPLETE
|
||||
|
||||
**Agent:** inspector
|
||||
**Story:** {{story_key}}
|
||||
**Status:** PASS | FAIL
|
||||
|
||||
### Evidence
|
||||
- **Type Check:** PASS (0 errors) | FAIL (X errors)
|
||||
- **Lint:** PASS (0 warnings) | FAIL (X warnings)
|
||||
- **Build:** PASS | FAIL
|
||||
- **Tests:** X passing, Y failing, Z% coverage
|
||||
|
||||
### Files Verified
|
||||
- path/to/file1.ts ✓
|
||||
- path/to/file2.ts ✓
|
||||
- path/to/missing.ts ✗ (NOT FOUND)
|
||||
|
||||
### Failures (if FAIL status)
|
||||
1. Specific failure with file:line reference
|
||||
2. Another specific failure
|
||||
|
||||
### Ready For
|
||||
- If PASS: Reviewer (next phase)
|
||||
- If FAIL: Builder needs to fix before proceeding
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**Remember:** You are the INSPECTOR. Your job is to find the truth, not rubber-stamp the Builder's work. If something is wrong, say so with evidence.
|
||||
|
|
|
|||
|
|
@ -187,4 +187,37 @@ Before completing review, check:
|
|||
|
||||
---
|
||||
|
||||
## When Complete, Return This Format
|
||||
|
||||
```markdown
|
||||
## AGENT COMPLETE
|
||||
|
||||
**Agent:** reviewer
|
||||
**Story:** {{story_key}}
|
||||
**Status:** ISSUES_FOUND | CLEAN
|
||||
|
||||
### Issue Summary
|
||||
- **CRITICAL:** X issues (security, data loss)
|
||||
- **HIGH:** X issues (production bugs)
|
||||
- **MEDIUM:** X issues (tech debt)
|
||||
- **LOW:** X issues (nice-to-have)
|
||||
- **TOTAL:** X issues
|
||||
|
||||
### Must Fix (CRITICAL + HIGH)
|
||||
1. [CRITICAL] file.ts:45 - SQL injection in user query
|
||||
2. [HIGH] file.ts:89 - Missing null check causes crash
|
||||
|
||||
### Should Fix (MEDIUM)
|
||||
1. file.ts:123 - No error handling for API call
|
||||
|
||||
### Files Reviewed
|
||||
- path/to/file1.ts ✓
|
||||
- path/to/file2.ts ✓
|
||||
|
||||
### Ready For
|
||||
Fixer agent to address CRITICAL and HIGH issues
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**Remember:** You are the ADVERSARIAL REVIEWER. Your success is measured by finding legitimate issues. Don't be nice - be thorough.
|
||||
|
|
|
|||
|
|
@ -1,15 +1,19 @@
|
|||
# Super-Dev Pipeline - Multi-Agent Architecture
|
||||
# Super-Dev-Pipeline v2.1 - Multi-Agent Architecture
|
||||
|
||||
**Version:** 2.1.0
|
||||
**Architecture:** GSDMAD (GSD + BMAD)
|
||||
**Philosophy:** Trust but verify, separation of concerns
|
||||
**Philosophy:** Agents do creative work, orchestrator does bookkeeping
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
This workflow implements a story using **4 independent agents** with external validation at each phase.
|
||||
This workflow implements a story using **4 independent agents** with orchestrator-driven reconciliation.
|
||||
|
||||
**Key Innovation:** Each agent has single responsibility and fresh context. No agent validates its own work.
|
||||
**Key Innovation:**
|
||||
- Each agent has single responsibility and fresh context
|
||||
- No agent validates its own work
|
||||
- **Orchestrator does bookkeeping** (story file updates, verification) - not agents
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -21,40 +25,48 @@ This workflow implements a story using **4 independent agents** with external va
|
|||
│ - Loads story │
|
||||
│ - Spawns agents sequentially │
|
||||
│ - Verifies each phase │
|
||||
│ - DOES RECONCILIATION DIRECTLY (not via agent) │
|
||||
│ - Final quality gate │
|
||||
└─────────────────────────────────────────────────────────────┘
|
||||
│
|
||||
├──> Phase 1: Builder (Steps 1-4)
|
||||
├──> Phase 1: Builder (Steps 1-4) [AGENT]
|
||||
│ - Load story, analyze gaps
|
||||
│ - Write tests (TDD)
|
||||
│ - Implement code
|
||||
│ - Report what was built (NO VALIDATION)
|
||||
│
|
||||
├──> Phase 2: Inspector (Steps 5-6)
|
||||
├──> Phase 2: Inspector (Steps 5-6) [AGENT]
|
||||
│ - Fresh context, no Builder knowledge
|
||||
│ - Verify files exist
|
||||
│ - Run tests independently
|
||||
│ - Run quality checks
|
||||
│ - PASS or FAIL verdict
|
||||
│
|
||||
├──> Phase 3: Reviewer (Step 7)
|
||||
├──> Phase 3: Reviewer (Step 7) [AGENT]
|
||||
│ - Fresh context, adversarial stance
|
||||
│ - Find security vulnerabilities
|
||||
│ - Find performance problems
|
||||
│ - Find logic bugs
|
||||
│ - Report issues with severity
|
||||
│
|
||||
├──> Phase 4: Fixer (Steps 8-9)
|
||||
├──> Phase 4: Fixer (Steps 8-9) [AGENT]
|
||||
│ - Fix CRITICAL issues (all)
|
||||
│ - Fix HIGH issues (all)
|
||||
│ - Fix MEDIUM issues (if time)
|
||||
│ - Skip LOW issues (gold-plating)
|
||||
│ - Update story + sprint-status
|
||||
│ - Commit changes
|
||||
│ - Commit code changes
|
||||
│
|
||||
└──> Final Verification (Main)
|
||||
├──> Phase 5: Reconciliation (Step 10) [ORCHESTRATOR] 🔧
|
||||
│ - Orchestrator uses Bash/Read/Edit tools directly
|
||||
│ - Check off completed tasks in story file
|
||||
│ - Fill Dev Agent Record with details
|
||||
│ - Verify updates with bash commands
|
||||
│ - BLOCKER if verification fails
|
||||
│
|
||||
└──> Final Verification [ORCHESTRATOR]
|
||||
- Check git commits exist
|
||||
- Check story checkboxes updated
|
||||
- Check story checkboxes updated (count > 0)
|
||||
- Check Dev Agent Record filled
|
||||
- Check sprint-status updated
|
||||
- Check tests passed
|
||||
- Mark COMPLETE or FAILED
|
||||
|
|
@ -182,45 +194,181 @@ Task({
|
|||
|
||||
**Wait for Fixer to complete.**
|
||||
|
||||
### Phase 5: Orchestrator Reconciliation (MANDATORY)
|
||||
|
||||
🚨 **THIS PHASE IS MANDATORY. ORCHESTRATOR DOES THIS DIRECTLY. NO AGENT SPAWN.** 🚨
|
||||
|
||||
**Why orchestrator, not agent?** Agents ignore instructions. The orchestrator has the context
|
||||
and can use tools directly. This is bookkeeping work, not creative work.
|
||||
|
||||
**YOU (the orchestrator) must execute these commands directly:**
|
||||
|
||||
**Step 5.1: Get what was built**
|
||||
```bash
|
||||
# Get commit for this story
|
||||
COMMIT_INFO=$(git log -5 --oneline | grep "{{story_key}}" | head -1)
|
||||
echo "Commit: $COMMIT_INFO"
|
||||
|
||||
# Get files changed (production code only)
|
||||
FILES_CHANGED=$(git diff HEAD~1 --name-only | grep -v "__tests__" | grep -v "\.test\." | grep -v "\.spec\.")
|
||||
echo "Files changed:"
|
||||
echo "$FILES_CHANGED"
|
||||
```
|
||||
|
||||
**Step 5.2: Read story file tasks**
|
||||
Use Read tool: `{{story_file}}`
|
||||
|
||||
Find the Tasks section and identify which tasks relate to the files changed.
|
||||
|
||||
**Step 5.3: Check off completed tasks**
|
||||
Use Edit tool for EACH task that was completed:
|
||||
```
|
||||
old_string: "- [ ] Task description here"
|
||||
new_string: "- [x] Task description here"
|
||||
```
|
||||
|
||||
**Step 5.4: Fill Dev Agent Record**
|
||||
Use Edit tool to update the Dev Agent Record section:
|
||||
```
|
||||
old_string: "### Dev Agent Record
|
||||
- **Agent Model Used:** [Not set]
|
||||
- **Implementation Date:** [Not set]
|
||||
- **Files Created/Modified:** [Not set]
|
||||
- **Tests Added:** [Not set]
|
||||
- **Completion Notes:** [Not set]"
|
||||
|
||||
new_string: "### Dev Agent Record
|
||||
- **Agent Model Used:** Claude Sonnet 4 (multi-agent: Builder + Inspector + Reviewer + Fixer)
|
||||
- **Implementation Date:** {{date}}
|
||||
- **Files Created/Modified:**
|
||||
{{#each files_changed}}
|
||||
- {{this}}
|
||||
{{/each}}
|
||||
- **Tests Added:** [count from Inspector report]
|
||||
- **Completion Notes:** [brief summary of what was implemented]"
|
||||
```
|
||||
|
||||
**Step 5.5: Verify updates (BLOCKER)**
|
||||
```bash
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "🔍 RECONCILIATION VERIFICATION"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
# Count checked tasks
|
||||
CHECKED=$(grep -c "^- \[x\]" {{story_file}})
|
||||
echo "Checked tasks: $CHECKED"
|
||||
|
||||
if [ "$CHECKED" -eq 0 ]; then
|
||||
echo "❌ BLOCKER: Zero checked tasks"
|
||||
echo "Go back to Step 5.3 and check off tasks"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Verify Dev Agent Record
|
||||
RECORD=$(grep -A 5 "### Dev Agent Record" {{story_file}} | grep -c "Implementation Date:")
|
||||
if [ "$RECORD" -eq 0 ]; then
|
||||
echo "❌ BLOCKER: Dev Agent Record not filled"
|
||||
echo "Go back to Step 5.4 and fill it"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✅ Reconciliation verified: $CHECKED tasks checked"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
```
|
||||
|
||||
**If verification fails:** DO NOT proceed. Fix immediately using Edit tool, then re-verify.
|
||||
|
||||
---
|
||||
|
||||
## Final Verification (Main Orchestrator)
|
||||
|
||||
**After all agents complete, verify:**
|
||||
🚨 **CRITICAL: This verification is MANDATORY. DO NOT skip.** 🚨
|
||||
|
||||
**After all agents complete (including Reconciler), YOU (the main orchestrator) must:**
|
||||
|
||||
1. **Use the Bash tool** to run these commands
|
||||
2. **Read the output** to see if verification passed
|
||||
3. **If verification fails**, use Edit and Bash tools to fix it NOW
|
||||
4. **Do not proceed** until verification passes
|
||||
|
||||
**COMMAND TO RUN WITH BASH TOOL:**
|
||||
|
||||
```bash
|
||||
# 1. Check git commits
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "🔍 FINAL VERIFICATION (MANDATORY)"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
# 1. Check git commits exist
|
||||
echo "Checking git commits..."
|
||||
git log --oneline -3 | grep "{{story_key}}"
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "❌ FAILED: No commit found"
|
||||
echo "❌ FAILED: No commit found for {{story_key}}"
|
||||
echo "The Fixer agent did not commit changes."
|
||||
exit 1
|
||||
fi
|
||||
echo "✅ Git commit found"
|
||||
|
||||
# 2. Check story checkboxes
|
||||
before=$(git show HEAD~1:{{story_file}} | grep -c '^- \[x\]')
|
||||
after=$(grep -c '^- \[x\]' {{story_file}})
|
||||
if [ $after -le $before ]; then
|
||||
echo "❌ FAILED: Checkboxes not updated"
|
||||
# 2. Check story file has checked tasks (ABSOLUTE BLOCKER)
|
||||
echo "Checking story file updates..."
|
||||
CHECKED_COUNT=$(grep -c '^- \[x\]' {{story_file}})
|
||||
echo "Checked tasks: $CHECKED_COUNT"
|
||||
|
||||
if [ "$CHECKED_COUNT" -eq 0 ]; then
|
||||
echo ""
|
||||
echo "❌ BLOCKER: Story file has ZERO checked tasks"
|
||||
echo ""
|
||||
echo "This means the Fixer agent did NOT update the story file."
|
||||
echo "The story CANNOT be marked complete without checked tasks."
|
||||
echo ""
|
||||
echo "You must:"
|
||||
echo " 1. Read the git commit to see what was built"
|
||||
echo " 2. Read the story Tasks section"
|
||||
echo " 3. Use Edit tool to check off completed tasks"
|
||||
echo " 4. Fill in Dev Agent Record"
|
||||
echo " 5. Verify with grep"
|
||||
echo " 6. Re-run this verification"
|
||||
echo ""
|
||||
exit 1
|
||||
fi
|
||||
echo "✅ Story file has $CHECKED_COUNT checked tasks"
|
||||
|
||||
# 3. Check sprint-status
|
||||
git diff HEAD~1 {{sprint_status}} | grep "{{story_key}}: done"
|
||||
# 3. Check Dev Agent Record filled
|
||||
echo "Checking Dev Agent Record..."
|
||||
RECORD_FILLED=$(grep -A 20 "^### Dev Agent Record" {{story_file}} | grep -c "Agent Model")
|
||||
if [ "$RECORD_FILLED" -eq 0 ]; then
|
||||
echo "❌ BLOCKER: Dev Agent Record NOT filled"
|
||||
echo "The Fixer agent did not document what was built."
|
||||
exit 1
|
||||
fi
|
||||
echo "✅ Dev Agent Record filled"
|
||||
|
||||
# 4. Check sprint-status updated
|
||||
echo "Checking sprint-status..."
|
||||
git diff HEAD~1 {{sprint_status}} | grep "{{story_key}}"
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "❌ FAILED: Sprint status not updated"
|
||||
echo "❌ FAILED: Sprint status not updated for {{story_key}}"
|
||||
exit 1
|
||||
fi
|
||||
echo "✅ Sprint status updated"
|
||||
|
||||
# 4. Check Inspector output for test evidence
|
||||
grep -E "PASS|tests.*passing" inspector_output.txt
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "❌ FAILED: No test evidence"
|
||||
exit 1
|
||||
# 5. Check test evidence (optional - may have test failures)
|
||||
echo "Checking test evidence..."
|
||||
if [ -f "inspector_output.txt" ]; then
|
||||
grep -E "PASS|tests.*passing" inspector_output.txt && echo "✅ Tests passing"
|
||||
fi
|
||||
|
||||
echo ""
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "✅ STORY COMPLETE - All verifications passed"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
```
|
||||
|
||||
**IF VERIFICATION FAILS:**
|
||||
- DO NOT mark story as "done"
|
||||
- DO NOT proceed to next story
|
||||
- FIX the failure immediately
|
||||
- Re-run verification until it passes
|
||||
|
||||
---
|
||||
|
||||
## Benefits Over Single-Agent
|
||||
|
|
|
|||
|
|
@ -67,6 +67,8 @@ agents:
|
|||
trust_level: "medium" # Incentive to minimize work
|
||||
timeout: 2400 # 40 minutes
|
||||
|
||||
# Reconciliation: orchestrator does this directly (see workflow.md Phase 5)
|
||||
|
||||
# Complexity level (determines which steps to execute)
|
||||
complexity_level: "standard" # micro | standard | complex
|
||||
|
||||
|
|
|
|||
|
|
@ -94,40 +94,30 @@ Run `/bmad_bmm_sprint-status` to see current status.</output>
|
|||
<example>Input: "20-11" → epic=20, story=11, suffix=""</example>
|
||||
</substep>
|
||||
|
||||
<substep n="2b" title="Check for story file using CANONICAL format only">
|
||||
<critical>🚨 ONE CANONICAL FORMAT - NO VARIATIONS</critical>
|
||||
<substep n="2b" title="Try multiple file patterns using Glob tool">
|
||||
<action>Use Glob tool to search for files matching these patterns (in priority order):</action>
|
||||
|
||||
<action>CANONICAL FORMAT: {story_key}.md</action>
|
||||
<example>20-9-megamenu-navigation.md (epic-story-slug, NO prefix)</example>
|
||||
<example>18-1-charge-model-state-machine.md (epic-story-slug, NO prefix)</example>
|
||||
<pattern n="1">story-{epic_num}.{story_num}.md</pattern>
|
||||
<example>story-20.9.md (DOT notation, no suffix)</example>
|
||||
|
||||
<action>Check if file exists: {sprint_artifacts}/{story_key}.md</action>
|
||||
<pattern n="2">story-{epic_num}.{story_num}*.md</pattern>
|
||||
<example>story-20.9-megamenu-navigation.md (DOT notation WITH suffix - use Glob wildcard)</example>
|
||||
|
||||
<check if="file exists">
|
||||
<action>Set file_status = ✅ EXISTS</action>
|
||||
<action>Store file_path = {sprint_artifacts}/{story_key}.md</action>
|
||||
</check>
|
||||
<pattern n="3">{epic_num}-{story_num}.md</pattern>
|
||||
<example>20-9.md (HYPHEN notation, no "story-" prefix)</example>
|
||||
|
||||
<check if="file does NOT exist">
|
||||
<action>Set file_status = ❌ MISSING</action>
|
||||
<pattern n="4">{epic_num}-{story_num}*.md</pattern>
|
||||
<example>20-9-megamenu-navigation.md (HYPHEN notation WITH suffix)</example>
|
||||
|
||||
<action>Check for legacy wrong-named files:</action>
|
||||
<action> Search for: story-{story_key}.md (wrong - has "story-" prefix)</action>
|
||||
<pattern n="5">story-{story_key}.md</pattern>
|
||||
<example>story-20-9-megamenu-navigation.md (literal story_key with "story-" prefix)</example>
|
||||
|
||||
<check if="found wrong-named file">
|
||||
<output>⚠️ Found legacy file: story-{story_key}.md</output>
|
||||
<output>🔧 AUTO-RENAMING to canonical: {story_key}.md</output>
|
||||
<pattern n="6">{story_key}.md</pattern>
|
||||
<example>20-9-megamenu-navigation.md (literal story_key)</example>
|
||||
|
||||
<action>Rename: mv story-{story_key}.md {story_key}.md</action>
|
||||
<action>Verify rename worked</action>
|
||||
<action>Set file_status = ✅ EXISTS (after rename)</action>
|
||||
<action>Store file_path = {sprint_artifacts}/{story_key}.md</action>
|
||||
</check>
|
||||
|
||||
<check if="no file found (canonical OR legacy)">
|
||||
<action>file_status = ❌ MISSING (genuinely missing)</action>
|
||||
</check>
|
||||
</check>
|
||||
<action>Stop at first match and store file_path</action>
|
||||
<action>If NO match found after all 6 patterns → file_status = ❌ MISSING</action>
|
||||
<action>If match found → file_status = ✅ EXISTS</action>
|
||||
</substep>
|
||||
|
||||
<action>Mark stories as: ✅ (file exists), ❌ (file missing), 🔄 (already implemented but not marked done)</action>
|
||||
|
|
@ -685,59 +675,24 @@ Gap analysis will happen just-in-time during implementation (Step 2 of super-dev
|
|||
</check>
|
||||
</check>
|
||||
|
||||
<output>🚀 Spawning {{needs_creation.length}} parallel agents for story creation...</output>
|
||||
|
||||
<action>Spawn Task agents in PARALLEL (send all Task calls in SINGLE message):</action>
|
||||
|
||||
<iterate>For each story in needs_creation:</iterate>
|
||||
|
||||
<substep n="2.7a" title="Spawn story creation agent">
|
||||
<action>
|
||||
Task tool call:
|
||||
- subagent_type: "general-purpose"
|
||||
- description: "Create story {{story_key}}"
|
||||
- prompt: "Create basic story file for {{story_key}}.
|
||||
<substep n="2.7a" title="Create individual story file">
|
||||
<output>📝 Creating story {{@index}}/{{needs_creation.length}}: {{story_key}}...</output>
|
||||
|
||||
INSTRUCTIONS:
|
||||
1. Read epic description from docs/epics.md (Epic {{epic_num}})
|
||||
2. Read PRD requirements (docs/prd-art-collective-tenants.md)
|
||||
3. Read architecture (docs/architecture-space-rentals.md)
|
||||
4. Extract FRs for this story from PRD
|
||||
5. Break down into 3-7 tasks with subtasks
|
||||
6. Create story file at: docs/sprint-artifacts/{{story_key}}.md
|
||||
7. Use template from: _bmad/bmm/workflows/4-implementation/create-story/template.md
|
||||
8. NO gap analysis (defer to implementation)
|
||||
9. Commit story file when complete
|
||||
10. Report: story file path
|
||||
|
||||
Mode: batch (lightweight, no codebase scanning)"
|
||||
- Store returned agent_id for tracking
|
||||
<action>Invoke workflow: /bmad_bmm_create-story</action>
|
||||
<action>Parameters:
|
||||
- story_key: {{story_key}}
|
||||
- epic_num: {{epic_num}}
|
||||
- mode: batch (auto-approve, minimal prompts)
|
||||
</action>
|
||||
</substep>
|
||||
|
||||
<output>
|
||||
⏳ Waiting for {{needs_creation.length}} parallel agents to complete...
|
||||
|
||||
Story creation agents:
|
||||
{{#each needs_creation}}
|
||||
- Agent {{@index}}: {{story_key}}
|
||||
{{/each}}
|
||||
</output>
|
||||
|
||||
<action>Wait for ALL agents to complete (blocking)</action>
|
||||
|
||||
<iterate>Check each agent output:</iterate>
|
||||
|
||||
<substep n="2.7b" title="Verify story creation results">
|
||||
<action>Parse agent output for {{story_key}}</action>
|
||||
|
||||
<check if="agent succeeded AND story file exists">
|
||||
<check if="story creation succeeded">
|
||||
<output>✅ Story created: {{story_key}}</output>
|
||||
<action>Verify file exists at docs/sprint-artifacts/{{story_key}}.md</action>
|
||||
<action>Mark story.needs_story_creation = false</action>
|
||||
</check>
|
||||
|
||||
<check if="agent failed OR story file missing">
|
||||
<check if="story creation failed">
|
||||
<output>❌ Failed to create story: {{story_key}}</output>
|
||||
<action>Add to failed_creations list</action>
|
||||
<action>Remove from selected_stories</action>
|
||||
|
|
@ -830,93 +785,25 @@ QUALITY OVER SPEED: Taking time to ensure correctness.
|
|||
<action>Set quality_multiplier = 1.5</action>
|
||||
</check>
|
||||
|
||||
<substep n="3.1" title="Automatic Dependency Analysis (from GSD)">
|
||||
<output>
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
📊 ANALYZING STORY DEPENDENCIES
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
</output>
|
||||
|
||||
<iterate>For each selected story:</iterate>
|
||||
|
||||
<action>Read story file Tasks section</action>
|
||||
<action>Analyze task descriptions for dependencies on other selected stories:</action>
|
||||
<action>
|
||||
Dependency detection rules:
|
||||
- Look for mentions of other story keys (e.g., "18-1", "18-2")
|
||||
- Look for phrases like "requires", "depends on", "needs", "after"
|
||||
- Look for file paths that other stories create
|
||||
- Look for models/services that other stories define
|
||||
</action>
|
||||
|
||||
<action>Build dependency map:
|
||||
story_key: {
|
||||
depends_on: [list of story keys this depends on],
|
||||
blocks: [list of story keys that depend on this]
|
||||
}
|
||||
</action>
|
||||
|
||||
<action>Compute waves using topological sort:</action>
|
||||
<action>
|
||||
Wave 1: Stories with no dependencies (can start immediately)
|
||||
Wave 2: Stories that only depend on Wave 1
|
||||
Wave 3: Stories that depend on Wave 2
|
||||
...
|
||||
</action>
|
||||
|
||||
<output>
|
||||
📊 **Dependency Analysis Complete**
|
||||
|
||||
{{#each waves}}
|
||||
**Wave {{@index}}** ({{count}} stories):
|
||||
{{#each stories}}
|
||||
- {{story_key}}{{#if depends_on}} [depends on: {{depends_on}}]{{/if}}
|
||||
{{/each}}
|
||||
{{/each}}
|
||||
|
||||
**Execution Strategy:**
|
||||
{{#if waves.length == 1}}
|
||||
✅ All stories are independent - can run fully in parallel
|
||||
{{else}}
|
||||
⚙️ Dependencies detected - wave-based execution recommended
|
||||
- Wave 1: {{wave_1_count}} stories (parallel)
|
||||
- Total waves: {{waves.length}}
|
||||
- Sequential time: {{total_time_sequential}}
|
||||
- Wave-based time: {{total_time_waves}} ({{time_savings}}% faster)
|
||||
{{/if}}
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
</output>
|
||||
</substep>
|
||||
|
||||
<ask>
|
||||
**How should these stories be processed?**
|
||||
|
||||
Options:
|
||||
- **S**: Sequential - Run stories one-by-one (Task agent finishes before next starts)
|
||||
- **P**: Parallel - Run stories concurrently (Multiple Task agents running simultaneously)
|
||||
- **sequential**: Run stories one-by-one in this session (slower, easier to monitor)
|
||||
- **parallel**: Spawn Task agents to process stories concurrently (faster, autonomous)
|
||||
|
||||
**Note:** Both modes use Task agents to keep story context out of the main thread.
|
||||
The only difference is the number running at once.
|
||||
|
||||
Enter: S or P
|
||||
Enter: sequential or parallel
|
||||
</ask>
|
||||
|
||||
<action>Capture response as: execution_strategy</action>
|
||||
<action>Capture response as: execution_mode</action>
|
||||
|
||||
<check if="execution_strategy == 's' OR execution_strategy == 'S'">
|
||||
<action>Set execution_mode = "sequential"</action>
|
||||
<check if="execution_mode == 'sequential'">
|
||||
<action>Set parallel_count = 1</action>
|
||||
<action>Set use_task_agents = true</action>
|
||||
<output>
|
||||
⏺ ✅ Sequential mode selected - stories will be processed one-by-one
|
||||
|
||||
Each story runs in its own Task agent. Agents execute sequentially (one completes before next starts).
|
||||
This keeps the main thread clean while maintaining easy monitoring.
|
||||
</output>
|
||||
<action>Set use_task_agents = false</action>
|
||||
<output>✅ Sequential mode selected - stories will be processed one-by-one in this session</output>
|
||||
</check>
|
||||
|
||||
<check if="execution_strategy == 'p' OR execution_strategy == 'P'">
|
||||
<action>Set execution_mode = "parallel"</action>
|
||||
<check if="execution_mode == 'parallel'">
|
||||
<action>Set use_task_agents = true</action>
|
||||
|
||||
<ask>
|
||||
|
|
@ -939,33 +826,26 @@ Enter number (2-10) or 'all':
|
|||
<check if="parallel_count was capped at 10">
|
||||
<output>⚠️ Requested {{original_count}} agents, capped at 10 (safety limit)</output>
|
||||
</check>
|
||||
|
||||
<output>
|
||||
⏺ ✅ Parallel mode selected - {{parallel_count}} Task agents will run concurrently
|
||||
|
||||
Each story runs in its own Task agent. Multiple agents execute in parallel for faster completion.
|
||||
</output>
|
||||
</check>
|
||||
|
||||
<output>
|
||||
## ⚙️ Execution Plan
|
||||
|
||||
**Mode:** {{execution_mode}}
|
||||
**Task Agents:** {{parallel_count}} {{#if parallel_count > 1}}running concurrently{{else}}running sequentially{{/if}}
|
||||
{{#if use_task_agents}}
|
||||
**Task Agents:** {{parallel_count}} running concurrently
|
||||
**Agent Type:** general-purpose (autonomous)
|
||||
{{else}}
|
||||
**Sequential processing** in current session
|
||||
{{/if}}
|
||||
|
||||
**Stories to process:** {{count}}
|
||||
**Estimated total time:**
|
||||
{{#if parallel_count > 1}}
|
||||
{{#if use_task_agents}}
|
||||
- With {{parallel_count}} agents: {{estimated_hours / parallel_count}} hours
|
||||
{{else}}
|
||||
- Sequential: {{estimated_hours}} hours
|
||||
{{/if}}
|
||||
|
||||
**Complexity Routing:**
|
||||
{{#each stories_by_complexity}}
|
||||
- {{complexity}}: {{count}} stories ({{pipeline_description}})
|
||||
{{/each}}
|
||||
</output>
|
||||
|
||||
<ask>Confirm execution plan? (yes/no):</ask>
|
||||
|
|
@ -980,476 +860,56 @@ Each story runs in its own Task agent. Multiple agents execute in parallel for f
|
|||
<action>Initialize counters: completed=0, failed=0, failed_stories=[], reconciliation_warnings=[], reconciliation_warnings_count=0</action>
|
||||
<action>Set start_time = current timestamp</action>
|
||||
|
||||
<check if="parallel_count == 1">
|
||||
<action>Jump to Step 4-Sequential (Task agents, one at a time)</action>
|
||||
<check if="use_task_agents == true">
|
||||
<action>Jump to Step 4-Parallel (Task Agent execution)</action>
|
||||
</check>
|
||||
|
||||
<check if="parallel_count > 1 AND waves.length > 1">
|
||||
<action>Jump to Step 4-Wave (Task agents, wave-based parallel)</action>
|
||||
</check>
|
||||
|
||||
<check if="parallel_count > 1 AND waves.length <= 1">
|
||||
<action>Jump to Step 4-Parallel (Task agents, multiple concurrent)</action>
|
||||
<check if="use_task_agents == false">
|
||||
<action>Continue to Step 4-Sequential (In-session execution)</action>
|
||||
</check>
|
||||
</step>
|
||||
|
||||
<step n="4-Wave" goal="Wave-based parallel execution">
|
||||
<output>
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🚀 WAVE-BASED PARALLEL PROCESSING STARTED
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
**Stories:** {{count}}
|
||||
**Total waves:** {{waves.length}}
|
||||
**Mode:** Task agents (parallel by wave)
|
||||
**Max concurrent agents:** {{parallel_count}}
|
||||
**Continue on failure:** {{continue_on_failure}}
|
||||
**Pattern:** Wave barrier (complete wave before next wave)
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
|
||||
📊 **Wave Plan (from dependency analysis):**
|
||||
{{#each waves}}
|
||||
Wave {{@index}}: {{count}} stories
|
||||
{{#each stories}}
|
||||
- {{story_key}}{{#if depends_on}} [depends on: {{depends_on}}]{{/if}}
|
||||
{{/each}}
|
||||
{{/each}}
|
||||
</output>
|
||||
|
||||
<action>Set abort_batch = false</action>
|
||||
|
||||
<iterate>For each wave in waves (in order):</iterate>
|
||||
|
||||
<substep n="4w-start" title="Start wave {{@index}}">
|
||||
<output>
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🌊 STARTING WAVE {{@index}}
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
Stories in this wave:
|
||||
{{#each stories}}
|
||||
- {{story_key}}{{#if depends_on}} (depends on: {{depends_on}}){{/if}}
|
||||
{{/each}}
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
</output>
|
||||
|
||||
<action>Initialize wave worker pool state:</action>
|
||||
<action>
|
||||
- wave_queue = stories
|
||||
- Resolve wave_queue items to full story objects by matching story_key in selected_stories (include complexity_level, story_file_path)
|
||||
- active_workers = {} (map of worker_id → {story_key, task_id, started_at})
|
||||
- completed_wave_stories = []
|
||||
- failed_wave_stories = []
|
||||
- next_story_index = 0
|
||||
- max_workers = min(parallel_count, wave_queue.length)
|
||||
</action>
|
||||
</substep>
|
||||
|
||||
<substep n="4w-init" title="Fill initial worker slots for wave {{@index}}">
|
||||
<output>
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔧 Initializing {{max_workers}} worker slots for Wave {{@index}}...
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
</output>
|
||||
|
||||
<action>Spawn first {{max_workers}} agents (or fewer if less stories):</action>
|
||||
|
||||
<iterate>While next_story_index < min(max_workers, wave_queue.length):</iterate>
|
||||
|
||||
<action>
|
||||
story_key = wave_queue[next_story_index].story_key
|
||||
complexity_level = wave_queue[next_story_index].complexity_level
|
||||
story_file_path = wave_queue[next_story_index].story_file_path
|
||||
worker_id = next_story_index + 1
|
||||
|
||||
Spawn Task agent:
|
||||
- subagent_type: "general-purpose"
|
||||
- description: "Implement story {{story_key}}"
|
||||
- prompt: "Execute super-dev-pipeline workflow for story {{story_key}}.
|
||||
|
||||
Story file: docs/sprint-artifacts/{{story_key}}.md
|
||||
Complexity: {{complexity_level}}
|
||||
Mode: batch
|
||||
|
||||
Load workflow: /Users/jonahschulte/git/BMAD-METHOD/src/modules/bmm/workflows/4-implementation/super-dev-pipeline
|
||||
Follow the multi-agent pipeline (builder, inspector, reviewer, fixer).
|
||||
Commit when complete, update story status, report results."
|
||||
- run_in_background: true (non-blocking)
|
||||
|
||||
Store in active_workers[worker_id]:
|
||||
story_key: {{story_key}}
|
||||
task_id: {{returned_task_id}}
|
||||
started_at: {{timestamp}}
|
||||
status: "running"
|
||||
</action>
|
||||
|
||||
<action>Increment next_story_index</action>
|
||||
<output>🚀 Worker {{worker_id}} started: {{story_key}}</output>
|
||||
</substep>
|
||||
|
||||
<substep n="4w-pool" title="Maintain wave worker pool for wave {{@index}}">
|
||||
<critical>WAVE BARRIER: Complete all stories in this wave before starting next wave</critical>
|
||||
|
||||
<iterate>While active_workers.size > 0 OR next_story_index < wave_queue.length:</iterate>
|
||||
|
||||
<action>Poll for completed workers (check task outputs non-blocking):</action>
|
||||
|
||||
<iterate>For each worker_id in active_workers:</iterate>
|
||||
|
||||
<action>Check if worker task completed using TaskOutput(task_id, block=false)</action>
|
||||
|
||||
<check if="worker task is still running">
|
||||
<action>Continue to next worker (don't wait)</action>
|
||||
</check>
|
||||
|
||||
<check if="worker task completed successfully">
|
||||
<action>Get worker details: story_key = active_workers[worker_id].story_key</action>
|
||||
|
||||
<output>✅ Worker {{worker_id}} completed: {{story_key}}</output>
|
||||
|
||||
<action>Execute Step 4.5: Smart Story Reconciliation</action>
|
||||
<action>Load reconciliation instructions: {installed_path}/step-4.5-reconcile-story-status.md</action>
|
||||
<action>Execute reconciliation with story_key={{story_key}}</action>
|
||||
|
||||
<critical>🚨 MANDATORY STORY FILE VERIFICATION - MAIN ORCHESTRATOR MUST RUN BASH</critical>
|
||||
|
||||
<bash_required>
|
||||
STORY_FILE="docs/sprint-artifacts/{{story_key}}.md"
|
||||
echo "🔍 Verifying story file: {{story_key}}"
|
||||
|
||||
CHECKED_COUNT=$(grep -c "^- \[x\]" "$STORY_FILE" 2>/dev/null || echo "0")
|
||||
TOTAL_COUNT=$(grep -c "^- \[.\]" "$STORY_FILE" 2>/dev/null || echo "0")
|
||||
echo " Checked tasks: $CHECKED_COUNT/$TOTAL_COUNT"
|
||||
|
||||
RECORD_FILLED=$(grep -A 20 "^### Dev Agent Record" "$STORY_FILE" 2>/dev/null | grep -c "Claude Sonnet" || echo "0")
|
||||
echo " Dev Agent Record: $RECORD_FILLED"
|
||||
|
||||
echo "$CHECKED_COUNT" > /tmp/checked_{{story_key}}.txt
|
||||
echo "$RECORD_FILLED" > /tmp/record_{{story_key}}.txt
|
||||
</bash_required>
|
||||
|
||||
<check if="checked_count == 0 OR record_filled == 0">
|
||||
<output>
|
||||
❌ Story {{story_key}}: Agent FAILED to update story file
|
||||
|
||||
Checked tasks: {{checked_tasks}}/{{total_tasks}}
|
||||
Dev Agent Record: {{dev_agent_record_status}}
|
||||
|
||||
🔧 EXECUTING AUTO-FIX RECONCILIATION...
|
||||
</output>
|
||||
|
||||
<action>AUTO-FIX PROCEDURE:</action>
|
||||
<action>1. Read agent's commit to see what files were created/modified</action>
|
||||
<action>2. Read story Tasks section to see what was supposed to be built</action>
|
||||
<action>3. For each task, check if corresponding code exists in commit</action>
|
||||
<action>4. If code exists, check off the task using Edit tool</action>
|
||||
<action>5. Fill in Dev Agent Record with commit details</action>
|
||||
<action>6. Verify fixes worked (re-count checked tasks)</action>
|
||||
|
||||
<check if="auto_fix_succeeded AND checked_tasks > 0">
|
||||
<output>✅ AUTO-FIX SUCCESS: {{checked_tasks}}/{{total_tasks}} tasks now checked</output>
|
||||
<action>Continue with story completion</action>
|
||||
</check>
|
||||
|
||||
<check if="auto_fix_failed OR checked_tasks still == 0">
|
||||
<output>
|
||||
❌ AUTO-FIX FAILED: Cannot reconcile story {{story_key}}
|
||||
|
||||
After auto-fix attempts:
|
||||
- Checked tasks: {{checked_tasks}}/{{total_tasks}}
|
||||
- Dev Agent Record: {{dev_agent_record_status}}
|
||||
|
||||
**Agent produced code but story file cannot be updated.**
|
||||
|
||||
Marking story as "in-progress" (not done) and continuing with warnings.
|
||||
</output>
|
||||
<action>Override story status to "in-progress"</action>
|
||||
<action>Add to reconciliation_warnings with detailed diagnostic</action>
|
||||
<action>Continue (do NOT kill workers)</action>
|
||||
</check>
|
||||
</check>
|
||||
|
||||
<check if="reconciliation succeeded AND checked_tasks > 0 AND dev_agent_record_filled">
|
||||
<output>✅ COMPLETED: {{story_key}} (reconciled and verified)</output>
|
||||
<output> Tasks: {{checked_tasks}}/{{total_tasks}} ({{task_completion_pct}}%)</output>
|
||||
<action>Increment completed counter</action>
|
||||
<action>Add to completed_wave_stories</action>
|
||||
</check>
|
||||
|
||||
<check if="task_completion_pct < 80">
|
||||
<output>⚠️ WARNING: {{story_key}} - Low completion ({{task_completion_pct}}%)</output>
|
||||
<action>Add to reconciliation_warnings: {story_key: {{story_key}}, warning_message: "Only {{task_completion_pct}}% tasks checked - manual verification needed"}</action>
|
||||
</check>
|
||||
|
||||
<action>Remove worker_id from active_workers (free the slot)</action>
|
||||
|
||||
<action>IMMEDIATELY refill slot if stories remain in this wave:</action>
|
||||
<check if="next_story_index < wave_queue.length">
|
||||
<action>story_key = wave_queue[next_story_index].story_key</action>
|
||||
<action>complexity_level = wave_queue[next_story_index].complexity_level</action>
|
||||
<action>story_file_path = wave_queue[next_story_index].story_file_path</action>
|
||||
|
||||
<output>🔄 Worker {{worker_id}} refilled: {{story_key}}</output>
|
||||
|
||||
<action>Spawn new Task agent for this worker_id (same parameters as init)</action>
|
||||
<action>Update active_workers[worker_id] with new task_id and story_key</action>
|
||||
<action>Increment next_story_index</action>
|
||||
</check>
|
||||
</check>
|
||||
|
||||
<check if="worker task failed">
|
||||
<action>Get worker details: story_key = active_workers[worker_id].story_key</action>
|
||||
|
||||
<output>❌ Worker {{worker_id}} failed: {{story_key}}</output>
|
||||
|
||||
<action>Increment failed counter</action>
|
||||
<action>Add story_key to failed_stories list</action>
|
||||
<action>Add to failed_wave_stories</action>
|
||||
<action>Remove worker_id from active_workers (free the slot)</action>
|
||||
|
||||
<check if="continue_on_failure == false">
|
||||
<output>⚠️ Stopping wave and batch due to failure (continue_on_failure=false)</output>
|
||||
<action>Kill all active workers</action>
|
||||
<action>Clear active_workers</action>
|
||||
<action>Set abort_batch = true</action>
|
||||
<action>Break worker pool loop</action>
|
||||
</check>
|
||||
|
||||
<check if="continue_on_failure == true AND next_story_index < wave_queue.length">
|
||||
<action>story_key = wave_queue[next_story_index].story_key</action>
|
||||
<action>complexity_level = wave_queue[next_story_index].complexity_level</action>
|
||||
<action>story_file_path = wave_queue[next_story_index].story_file_path</action>
|
||||
|
||||
<output>🔄 Worker {{worker_id}} refilled: {{story_key}} (despite previous failure)</output>
|
||||
|
||||
<action>Spawn new Task agent for this worker_id</action>
|
||||
<action>Update active_workers[worker_id] with new task_id and story_key</action>
|
||||
<action>Increment next_story_index</action>
|
||||
</check>
|
||||
</check>
|
||||
|
||||
<check if="abort_batch == true">
|
||||
<action>Break worker pool loop</action>
|
||||
</check>
|
||||
|
||||
<action>Display live progress every 30 seconds:</action>
|
||||
<output>
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
📊 Live Progress (Wave {{@index}} - {{timestamp}})
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
✅ Completed: {{completed}}
|
||||
❌ Failed: {{failed}}
|
||||
🔄 Active workers: {{active_workers.size}}
|
||||
📋 Queued in wave: {{wave_queue.length - next_story_index}}
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
</output>
|
||||
|
||||
<action>Sleep 5 seconds before next poll (prevents tight loop)</action>
|
||||
|
||||
</substep>
|
||||
|
||||
<check if="abort_batch == true">
|
||||
<output>⛔ Aborting remaining waves due to failure and continue_on_failure=false</output>
|
||||
<action>Jump to Step 5 (Summary)</action>
|
||||
</check>
|
||||
|
||||
<output>
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
✅ WAVE {{@index}} COMPLETE
|
||||
Stories completed: {{completed_wave_stories.length}}
|
||||
Stories failed: {{failed_wave_stories.length}}
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
</output>
|
||||
|
||||
<action>After all waves processed, jump to Step 5 (Summary)</action>
|
||||
</step>
|
||||
|
||||
<step n="4-Sequential" goal="Sequential Task agent execution (one at a time)">
|
||||
<step n="4-Sequential" goal="Sequential processing in current session">
|
||||
<output>
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🚀 SEQUENTIAL BATCH PROCESSING STARTED
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
**Stories:** {{count}}
|
||||
**Mode:** Task agents (sequential, one at a time)
|
||||
**Mode:** super-dev-pipeline (batch, sequential)
|
||||
**Continue on failure:** {{continue_on_failure}}
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
</output>
|
||||
|
||||
<iterate>For each story in selected_stories:</iterate>
|
||||
|
||||
<substep n="4s-a" title="Spawn Task agent for story">
|
||||
<substep n="4s-a" title="Process individual story">
|
||||
<output>
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
📦 Story {{current_index}}/{{total_count}}: {{story_key}}
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
|
||||
Complexity: {{complexity_level}}
|
||||
Pipeline: {{#if complexity_level == 'micro'}}Lightweight (skip tests, skip review){{else if complexity_level == 'standard'}}Full quality gates{{else}}Enhanced validation{{/if}}
|
||||
|
||||
Spawning Task agent...
|
||||
</output>
|
||||
|
||||
<action>
|
||||
Use Task tool to spawn agent:
|
||||
- subagent_type: "general-purpose"
|
||||
- description: "Implement story {{story_key}}"
|
||||
- prompt: "Execute super-dev-pipeline workflow for story {{story_key}}.
|
||||
<action>Invoke workflow: /bmad:bmm:workflows:super-dev-pipeline</action>
|
||||
<action>Parameters: mode=batch, story_key={{story_key}}, complexity_level={{story_key}}.complexity.level</action>
|
||||
|
||||
Story file: docs/sprint-artifacts/{{story_key}}.md
|
||||
Complexity: {{complexity_level}}
|
||||
Mode: batch
|
||||
|
||||
Load workflow: /Users/jonahschulte/git/BMAD-METHOD/src/modules/bmm/workflows/4-implementation/super-dev-pipeline
|
||||
Follow the multi-agent pipeline (builder, inspector, reviewer, fixer).
|
||||
Commit when complete, update story status, report results."
|
||||
- Store agent_id
|
||||
</action>
|
||||
|
||||
<action>WAIT for agent to complete (blocking call)</action>
|
||||
|
||||
<check if="Task agent succeeded">
|
||||
<check if="super-dev-pipeline succeeded">
|
||||
<output>✅ Implementation complete: {{story_key}}</output>
|
||||
|
||||
<critical>🚨 STORY RECONCILIATION - ORCHESTRATOR DOES THIS NOW (NOT AGENTS)</critical>
|
||||
<critical>ORCHESTRATOR: You must execute reconciliation directly using Bash/Read/Edit tools.</critical>
|
||||
<critical>Do NOT delegate this to an agent. YOU do it.</critical>
|
||||
|
||||
<output>
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔧 RECONCILING STORY FILE: {{story_key}}
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
Main orchestrator performing reconciliation (not delegating)
|
||||
</output>
|
||||
<reconciliation>
|
||||
1. Use Bash: `git log -3 --oneline | grep "{{story_key}}"` to find commit
|
||||
2. Use Bash: `git diff HEAD~1 --name-only` to get files changed
|
||||
3. Use Read: `docs/sprint-artifacts/{{story_key}}.md` to see tasks
|
||||
4. Use Edit: Check off tasks (change `- [ ]` to `- [x]`) for completed work
|
||||
5. Use Edit: Fill Dev Agent Record with files/date/summary
|
||||
6. Use Bash: Verify with `grep -c "^- \[x\]"` (must be > 0)
|
||||
7. Use Edit: Update sprint-status.yaml to "done" or "review"
|
||||
</reconciliation>
|
||||
|
||||
<action>YOU (orchestrator) must use Bash tool NOW with this command:</action>
|
||||
|
||||
<bash_command>
|
||||
STORY_FILE="docs/sprint-artifacts/{{story_key}}.md"
|
||||
|
||||
echo "Verifying story file: $STORY_FILE"
|
||||
|
||||
CHECKED_COUNT=$(grep -c "^- \[x\]" "$STORY_FILE" 2>/dev/null || echo "0")
|
||||
TOTAL_COUNT=$(grep -c "^- \[.\]" "$STORY_FILE" 2>/dev/null || echo "0")
|
||||
echo "Checked tasks: $CHECKED_COUNT/$TOTAL_COUNT"
|
||||
|
||||
RECORD_FILLED=$(grep -A 20 "^### Dev Agent Record" "$STORY_FILE" 2>/dev/null | grep -c "Claude Sonnet" || echo "0")
|
||||
echo "Dev Agent Record: $RECORD_FILLED"
|
||||
|
||||
echo "checked_count=$CHECKED_COUNT"
|
||||
echo "record_filled=$RECORD_FILLED"
|
||||
</bash_command>
|
||||
|
||||
<action>After running Bash tool, read the output and extract checked_count and record_filled values</action>
|
||||
|
||||
<check if="checked_count == 0 OR record_filled == 0">
|
||||
<output>
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
❌ STORY FILE VERIFICATION FAILED
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
|
||||
Story: {{story_key}}
|
||||
Checked tasks: {{checked_count}}/{{total_count}}
|
||||
Dev Agent Record: {{#if record_filled > 0}}FILLED{{else}}EMPTY{{/if}}
|
||||
|
||||
🚨 The agent DID NOT update the story file.
|
||||
|
||||
YOU (the main orchestrator) must fix this NOW.
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
</output>
|
||||
|
||||
<critical>MANDATORY AUTO-FIX - MAIN ORCHESTRATOR MUST EXECUTE THIS</critical>
|
||||
|
||||
<action>AUTO-FIX PROCEDURE (YOU MUST DO THIS):</action>
|
||||
|
||||
<bash_required>
|
||||
# Step 1: Get commit for this story
|
||||
COMMIT_SHA=$(git log -1 --grep="{{story_key}}" --pretty=format:"%H" 2>/dev/null)
|
||||
if [ -z "$COMMIT_SHA" ]; then
|
||||
# Try finding by story key pattern
|
||||
COMMIT_SHA=$(git log -5 --pretty=format:"%H %s" | grep -i "{{story_key}}" | head -1 | cut -d' ' -f1)
|
||||
fi
|
||||
|
||||
echo "Found commit: $COMMIT_SHA"
|
||||
|
||||
# Step 2: Get files changed
|
||||
git diff ${COMMIT_SHA}~1 $COMMIT_SHA --name-only | grep -v "test/" | grep -v "__tests__"
|
||||
</bash_required>
|
||||
|
||||
<action>Step 3: Read story file to get Tasks section:</action>
|
||||
<read_required>docs/sprint-artifacts/{{story_key}}.md</read_required>
|
||||
|
||||
<action>Step 4: For EACH task in Tasks section:</action>
|
||||
<iterate>For each line starting with "- [ ]":</iterate>
|
||||
|
||||
<action>
|
||||
- Extract task description
|
||||
- Check if git diff contains related file/function
|
||||
- If YES: Use Edit tool to change "- [ ]" to "- [x]"
|
||||
- Verify edit: Run bash grep to confirm checkbox is now checked
|
||||
</action>
|
||||
|
||||
<action>Step 5: Fill Dev Agent Record using Edit tool:</action>
|
||||
<action>
|
||||
- Find "### Dev Agent Record" section
|
||||
- Replace with actual data:
|
||||
* Agent Model: Claude Sonnet 4.5 (multi-agent pipeline)
|
||||
* Date: {{current_date}}
|
||||
* Files: {{files_from_git_diff}}
|
||||
* Notes: {{from_commit_message}}
|
||||
</action>
|
||||
|
||||
<action>Step 6: Re-run verification bash commands:</action>
|
||||
|
||||
<bash_required>
|
||||
CHECKED_COUNT=$(grep -c "^- \[x\]" "$STORY_FILE")
|
||||
RECORD_FILLED=$(grep -A 20 "^### Dev Agent Record" "$STORY_FILE" | grep -c "Claude Sonnet")
|
||||
|
||||
echo "After auto-fix:"
|
||||
echo " Checked tasks: $CHECKED_COUNT"
|
||||
echo " Dev Agent Record: $RECORD_FILLED"
|
||||
|
||||
if [ "$CHECKED_COUNT" -eq 0 ]; then
|
||||
echo "❌ AUTO-FIX FAILED: Story file still not updated"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✅ AUTO-FIX SUCCESS"
|
||||
</bash_required>
|
||||
|
||||
<check if="auto_fix_bash_exit_code == 0">
|
||||
<output>✅ AUTO-FIX SUCCESS: Story file now updated ({{checked_count}} tasks checked)</output>
|
||||
<action>Continue with story as completed</action>
|
||||
</check>
|
||||
|
||||
<check if="auto_fix_bash_exit_code != 0">
|
||||
<output>
|
||||
❌ AUTO-FIX FAILED: Cannot reconcile story {{story_key}}
|
||||
|
||||
After multiple fix attempts, story file still shows:
|
||||
- Checked tasks: {{checked_count}}
|
||||
- Dev Agent Record: {{record_status}}
|
||||
|
||||
Marking story as "in-progress" (not done).
|
||||
</output>
|
||||
<action>Update sprint-status to "in-progress" instead of "done"</action>
|
||||
<action>Add to failed_stories list</action>
|
||||
<action>Continue to next story (if continue_on_failure)</action>
|
||||
</check>
|
||||
</check>
|
||||
|
||||
<check if="task_completion_pct < 80">
|
||||
<output>
|
||||
⚠️ WARNING: Story {{story_key}} - LOW TASK COMPLETION
|
||||
|
||||
Only {{checked_tasks}}/{{total_tasks}} tasks checked ({{task_completion_pct}}%).
|
||||
|
||||
This suggests incomplete implementation. Cannot mark as "done".
|
||||
Marking as "in-progress" instead.
|
||||
</output>
|
||||
<action>Override story status to "in-progress"</action>
|
||||
<action>Override sprint-status to "in-progress"</action>
|
||||
<action>Add to reconciliation_warnings</action>
|
||||
</check>
|
||||
|
||||
<check if="reconciliation succeeded AND checked_tasks > 0 AND dev_agent_record_filled">
|
||||
<output>✅ COMPLETED: {{story_key}} (reconciled and verified)</output>
|
||||
<output> Tasks: {{checked_tasks}}/{{total_tasks}} ({{task_completion_pct}}%)</output>
|
||||
<check if="reconciliation succeeded (checked tasks > 0)">
|
||||
<output>✅ COMPLETED: {{story_key}} (reconciled)</output>
|
||||
<action>Increment completed counter</action>
|
||||
|
||||
<check if="execution_mode == 'interactive_checkpoint'">
|
||||
|
|
@ -1594,13 +1054,15 @@ Press [C] to continue or [P] to pause:
|
|||
- description: "Implement story {{story_key}}"
|
||||
- prompt: "Execute super-dev-pipeline workflow for story {{story_key}}.
|
||||
|
||||
Story file: docs/sprint-artifacts/{{story_key}}.md
|
||||
Complexity: {{complexity_level}}
|
||||
Mode: batch
|
||||
CRITICAL INSTRUCTIONS:
|
||||
1. Load workflow.xml: _bmad/core/tasks/workflow.xml
|
||||
2. Load workflow config: _bmad/bmm/workflows/4-implementation/super-dev-pipeline/workflow.yaml
|
||||
3. Execute in BATCH mode with story_key={{story_key}} and complexity_level={{story_key}}.complexity.level
|
||||
4. Follow all 7 pipeline steps (init, pre-gap, implement, post-validate, code-review, complete, summary)
|
||||
5. Commit changes when complete
|
||||
6. Report final status (done/failed) with file list
|
||||
|
||||
Load workflow: /Users/jonahschulte/git/BMAD-METHOD/src/modules/bmm/workflows/4-implementation/super-dev-pipeline
|
||||
Follow the multi-agent pipeline (builder, inspector, reviewer, fixer).
|
||||
Commit when complete, update story status, report results."
|
||||
Story file will be auto-resolved from multiple naming conventions."
|
||||
- run_in_background: true (non-blocking - critical for semaphore pattern)
|
||||
|
||||
Store in active_workers[worker_id]:
|
||||
|
|
@ -1643,77 +1105,27 @@ Press [C] to continue or [P] to pause:
|
|||
|
||||
<output>✅ Worker {{worker_id}} completed: {{story_key}}</output>
|
||||
|
||||
<action>Execute Step 4.5: Smart Story Reconciliation</action>
|
||||
<action>Load reconciliation instructions: {installed_path}/step-4.5-reconcile-story-status.md</action>
|
||||
<action>Execute reconciliation with story_key={{story_key}}</action>
|
||||
<critical>ORCHESTRATOR: You must execute reconciliation directly using Bash/Read/Edit tools.</critical>
|
||||
|
||||
<critical>🚨 MANDATORY STORY FILE VERIFICATION - MAIN ORCHESTRATOR MUST RUN BASH</critical>
|
||||
<reconciliation>
|
||||
1. Use Bash: `git log -3 --oneline | grep "{{story_key}}"` to find commit
|
||||
2. Use Bash: `git diff HEAD~1 --name-only` to get files changed
|
||||
3. Use Read: `docs/sprint-artifacts/{{story_key}}.md` to see tasks
|
||||
4. Use Edit: Check off tasks (change `- [ ]` to `- [x]`) for completed work
|
||||
5. Use Edit: Fill Dev Agent Record with files/date/summary
|
||||
6. Use Bash: Verify with `grep -c "^- \[x\]"` (must be > 0)
|
||||
7. Use Edit: Update sprint-status.yaml to "done" or "review"
|
||||
</reconciliation>
|
||||
|
||||
<bash_required>
|
||||
STORY_FILE="docs/sprint-artifacts/{{story_key}}.md"
|
||||
echo "🔍 Verifying story file: {{story_key}}"
|
||||
|
||||
CHECKED_COUNT=$(grep -c "^- \[x\]" "$STORY_FILE" 2>/dev/null || echo "0")
|
||||
TOTAL_COUNT=$(grep -c "^- \[.\]" "$STORY_FILE" 2>/dev/null || echo "0")
|
||||
echo " Checked tasks: $CHECKED_COUNT/$TOTAL_COUNT"
|
||||
|
||||
RECORD_FILLED=$(grep -A 20 "^### Dev Agent Record" "$STORY_FILE" 2>/dev/null | grep -c "Claude Sonnet" || echo "0")
|
||||
echo " Dev Agent Record: $RECORD_FILLED"
|
||||
|
||||
echo "$CHECKED_COUNT" > /tmp/checked_{{story_key}}.txt
|
||||
echo "$RECORD_FILLED" > /tmp/record_{{story_key}}.txt
|
||||
</bash_required>
|
||||
|
||||
<check if="checked_count == 0 OR record_filled == 0">
|
||||
<output>
|
||||
❌ Story {{story_key}}: Agent FAILED to update story file
|
||||
|
||||
Checked tasks: {{checked_tasks}}/{{total_tasks}}
|
||||
Dev Agent Record: {{dev_agent_record_status}}
|
||||
|
||||
🔧 EXECUTING AUTO-FIX RECONCILIATION...
|
||||
</output>
|
||||
|
||||
<action>AUTO-FIX PROCEDURE:</action>
|
||||
<action>1. Read agent's commit to see what files were created/modified</action>
|
||||
<action>2. Read story Tasks section to see what was supposed to be built</action>
|
||||
<action>3. For each task, check if corresponding code exists in commit</action>
|
||||
<action>4. If code exists, check off the task using Edit tool</action>
|
||||
<action>5. Fill in Dev Agent Record with commit details</action>
|
||||
<action>6. Verify fixes worked (re-count checked tasks)</action>
|
||||
|
||||
<check if="auto_fix_succeeded AND checked_tasks > 0">
|
||||
<output>✅ AUTO-FIX SUCCESS: {{checked_tasks}}/{{total_tasks}} tasks now checked</output>
|
||||
<action>Continue with story completion</action>
|
||||
</check>
|
||||
|
||||
<check if="auto_fix_failed OR checked_tasks still == 0">
|
||||
<output>
|
||||
❌ AUTO-FIX FAILED: Cannot reconcile story {{story_key}}
|
||||
|
||||
After auto-fix attempts:
|
||||
- Checked tasks: {{checked_tasks}}/{{total_tasks}}
|
||||
- Dev Agent Record: {{dev_agent_record_status}}
|
||||
|
||||
**Agent produced code but story file cannot be updated.**
|
||||
|
||||
Marking story as "in-progress" (not done) and continuing with warnings.
|
||||
</output>
|
||||
<action>Override story status to "in-progress"</action>
|
||||
<action>Add to reconciliation_warnings with detailed diagnostic</action>
|
||||
<action>Continue (do NOT kill workers)</action>
|
||||
</check>
|
||||
</check>
|
||||
|
||||
<check if="reconciliation succeeded AND checked_tasks > 0 AND dev_agent_record_filled">
|
||||
<output>✅ COMPLETED: {{story_key}} (reconciled and verified)</output>
|
||||
<output> Tasks: {{checked_tasks}}/{{total_tasks}} ({{task_completion_pct}}%)</output>
|
||||
<check if="reconciliation succeeded (checked tasks > 0)">
|
||||
<output>✅ COMPLETED: {{story_key}} (reconciled)</output>
|
||||
<action>Add to completed_stories</action>
|
||||
</check>
|
||||
|
||||
<check if="task_completion_pct < 80">
|
||||
<output>⚠️ WARNING: {{story_key}} - Low completion ({{task_completion_pct}}%)</output>
|
||||
<action>Add to reconciliation_warnings: {story_key: {{story_key}}, warning_message: "Only {{task_completion_pct}}% tasks checked - manual verification needed"}</action>
|
||||
<check if="reconciliation failed (checked tasks = 0)">
|
||||
<output>⚠️ WARNING: {{story_key}} completed but reconciliation failed</output>
|
||||
<action>Add to completed_stories (implementation successful)</action>
|
||||
<action>Add to reconciliation_warnings: {story_key: {{story_key}}, warning_message: "Reconciliation failed - manual verification needed"}</action>
|
||||
</check>
|
||||
|
||||
<action>Remove worker_id from active_workers (free the slot)</action>
|
||||
|
|
|
|||
|
|
@ -1,390 +1,171 @@
|
|||
# Step 4.5: Smart Story Reconciliation
|
||||
# Step 4.5: Story Reconciliation (Orchestrator-Driven)
|
||||
|
||||
<critical>Execute AFTER super-dev-pipeline completes but BEFORE marking story as "completed"</critical>
|
||||
<critical>This ensures story checkboxes and status accurately reflect actual implementation</critical>
|
||||
|
||||
## Goal
|
||||
|
||||
Verify story file accuracy by reconciling:
|
||||
1. **Acceptance Criteria checkboxes** vs Dev Agent Record
|
||||
2. **Tasks/Subtasks checkboxes** vs Dev Agent Record
|
||||
3. **Definition of Done checkboxes** vs Dev Agent Record
|
||||
4. **Story status** (should be "done" if implementation complete)
|
||||
5. **sprint-status.yaml entry** (should match story file status)
|
||||
**Version:** 2.1.0
|
||||
**Execute:** AFTER super-dev-pipeline completes, BEFORE marking story done
|
||||
**Who:** Orchestrator (YOU) - not an agent
|
||||
|
||||
---
|
||||
|
||||
## Execution
|
||||
## Why Orchestrator Does This
|
||||
|
||||
### 1. Load Story File
|
||||
|
||||
<action>Read story file: {story_file_path}</action>
|
||||
<action>Extract sections:
|
||||
- Acceptance Criteria (## Acceptance Criteria)
|
||||
- Tasks / Subtasks (## Tasks / Subtasks)
|
||||
- Definition of Done (## Definition of Done)
|
||||
- Dev Agent Record (## Dev Agent Record)
|
||||
- Story status header (**Status:** ...)
|
||||
</action>
|
||||
|
||||
### 2. Analyze Dev Agent Record
|
||||
|
||||
<action>Read "Dev Agent Record" section</action>
|
||||
|
||||
<check if="Dev Agent Record is empty or says '(To be filled by dev agent)'">
|
||||
<output>⚠️ Story {{story_key}}: Dev Agent Record is empty - cannot reconcile</output>
|
||||
<output>This suggests super-dev-pipeline did not complete successfully.</output>
|
||||
<action>Mark story as FAILED reconciliation</action>
|
||||
<action>Return early (skip remaining checks)</action>
|
||||
</check>
|
||||
|
||||
<action>Parse Dev Agent Record fields:
|
||||
- **Agent Model Used** (should have model name, not empty)
|
||||
- **Implementation Summary** (should describe what was built)
|
||||
- **File List** (should list new/modified files)
|
||||
- **Test Results** (should show test counts)
|
||||
- **Completion Notes** (should document what works)
|
||||
</action>
|
||||
|
||||
<check if="Implementation Summary contains 'COMPLETE' or lists specific deliverables">
|
||||
<action>Set implementation_status = COMPLETE</action>
|
||||
</check>
|
||||
|
||||
<check if="Implementation Summary is vague or says 'pending'">
|
||||
<action>Set implementation_status = INCOMPLETE</action>
|
||||
<output>⚠️ Story {{story_key}}: Implementation appears incomplete based on Dev Agent Record</output>
|
||||
</check>
|
||||
|
||||
### 3. Reconcile Acceptance Criteria
|
||||
|
||||
<action>For each AC subsection (AC1, AC2, AC3, AC4, etc.):</action>
|
||||
|
||||
<iterate>For each checkbox in AC section:</iterate>
|
||||
|
||||
<substep n="3a" title="Identify expected status from Dev Agent Record">
|
||||
<action>Search Implementation Summary and File List for keywords from checkbox text</action>
|
||||
|
||||
<example>
|
||||
Checkbox: "[ ] FlexibleGridSection component (renders dynamic grid layouts)"
|
||||
Implementation Summary mentions: "FlexibleGridSection component created"
|
||||
File List includes: "FlexibleGridSection.tsx"
|
||||
→ Expected status: CHECKED
|
||||
</example>
|
||||
|
||||
<action>Determine expected_checkbox_status:
|
||||
- CHECKED if Implementation Summary confirms it OR File List shows created files OR Test Results mention it
|
||||
- UNCHECKED if no evidence in Dev Agent Record
|
||||
- PARTIAL if mentioned as "pending" or "infrastructure ready"
|
||||
</action>
|
||||
</substep>
|
||||
|
||||
<substep n="3b" title="Compare actual vs expected">
|
||||
<action>Read actual checkbox state from story file ([x] vs [ ] vs [~])</action>
|
||||
|
||||
<check if="actual != expected">
|
||||
<output>🔧 Reconciling AC: "{{checkbox_text}}"
|
||||
Actual: {{actual_status}}
|
||||
Expected: {{expected_status}}
|
||||
Reason: {{evidence_from_dev_record}}
|
||||
</output>
|
||||
<action>Add to reconciliation_changes list</action>
|
||||
</check>
|
||||
</substep>
|
||||
|
||||
<action>After checking all ACs:
|
||||
- Count total AC items
|
||||
- Count checked AC items (after reconciliation)
|
||||
- Calculate AC completion percentage
|
||||
</action>
|
||||
|
||||
### 4. Reconcile Tasks / Subtasks
|
||||
|
||||
<action>For each Task (Task 1, Task 2, etc.):</action>
|
||||
|
||||
<iterate>For each checkbox in Tasks section:</iterate>
|
||||
|
||||
<substep n="4a" title="Identify expected status from Dev Agent Record">
|
||||
<action>Search Implementation Summary and File List for task keywords</action>
|
||||
|
||||
<example>
|
||||
Task checkbox: "[ ] **2.2:** Create FlexibleGridSection component"
|
||||
File List includes: "apps/frontend/web/src/components/FlexibleGridSection.tsx"
|
||||
→ Expected status: CHECKED
|
||||
</example>
|
||||
|
||||
<action>Determine expected_checkbox_status using same logic as AC section</action>
|
||||
</substep>
|
||||
|
||||
<substep n="4b" title="Compare and reconcile">
|
||||
<action>Read actual checkbox state</action>
|
||||
|
||||
<check if="actual != expected">
|
||||
<output>🔧 Reconciling Task: "{{task_text}}"
|
||||
Actual: {{actual_status}}
|
||||
Expected: {{expected_status}}
|
||||
Reason: {{evidence_from_dev_record}}
|
||||
</output>
|
||||
<action>Add to reconciliation_changes list</action>
|
||||
</check>
|
||||
</substep>
|
||||
|
||||
<action>After checking all Tasks:
|
||||
- Count total task items
|
||||
- Count checked task items (after reconciliation)
|
||||
- Calculate task completion percentage
|
||||
</action>
|
||||
|
||||
### 5. Reconcile Definition of Done
|
||||
|
||||
<action>For each DoD category (Code Quality, Testing, Security, etc.):</action>
|
||||
|
||||
<iterate>For each checkbox in DoD section:</iterate>
|
||||
|
||||
<substep n="5a" title="Determine expected status">
|
||||
<action>Check Test Results, Completion Notes for evidence</action>
|
||||
|
||||
<example>
|
||||
DoD checkbox: "[ ] Type check passes: `pnpm type-check` (zero errors)"
|
||||
Completion Notes say: "Type check passes ✅"
|
||||
→ Expected status: CHECKED
|
||||
</example>
|
||||
|
||||
<example>
|
||||
DoD checkbox: "[ ] Unit tests: 90%+ coverage"
|
||||
Test Results say: "37 tests passing"
|
||||
Completion Notes say: "100% coverage on FlexibleGridSection"
|
||||
→ Expected status: CHECKED
|
||||
</example>
|
||||
|
||||
<action>Determine expected_checkbox_status</action>
|
||||
</substep>
|
||||
|
||||
<substep n="5b" title="Compare and reconcile">
|
||||
<action>Read actual checkbox state</action>
|
||||
|
||||
<check if="actual != expected">
|
||||
<output>🔧 Reconciling DoD: "{{dod_text}}"
|
||||
Actual: {{actual_status}}
|
||||
Expected: {{expected_status}}
|
||||
Reason: {{evidence_from_dev_record}}
|
||||
</output>
|
||||
<action>Add to reconciliation_changes list</action>
|
||||
</check>
|
||||
</substep>
|
||||
|
||||
<action>After checking all DoD items:
|
||||
- Count total DoD items
|
||||
- Count checked DoD items (after reconciliation)
|
||||
- Calculate DoD completion percentage
|
||||
</action>
|
||||
|
||||
### 6. Determine Correct Story Status
|
||||
|
||||
<action>Based on completion percentages, determine correct story status:</action>
|
||||
|
||||
<check if="AC >= 95% AND Tasks >= 95% AND DoD >= 95%">
|
||||
<action>Set correct_story_status = "done"</action>
|
||||
</check>
|
||||
|
||||
<check if="AC >= 80% AND Tasks >= 80% AND DoD >= 80%">
|
||||
<action>Set correct_story_status = "review"</action>
|
||||
</check>
|
||||
|
||||
<check if="AC < 80% OR Tasks < 80% OR DoD < 80%">
|
||||
<action>Set correct_story_status = "in-progress"</action>
|
||||
</check>
|
||||
|
||||
<check if="implementation_status == INCOMPLETE">
|
||||
<action>Override: Set correct_story_status = "in-progress"</action>
|
||||
<output>⚠️ Overriding status to "in-progress" due to incomplete implementation</output>
|
||||
</check>
|
||||
|
||||
<action>Read current story status from story file (**Status:** ...)</action>
|
||||
|
||||
<check if="current_story_status != correct_story_status">
|
||||
<output>🔧 Story status mismatch:
|
||||
Current: {{current_story_status}}
|
||||
Expected: {{correct_story_status}}
|
||||
Reason: AC={{ac_pct}}% Tasks={{tasks_pct}}% DoD={{dod_pct}}%
|
||||
</output>
|
||||
<action>Add to reconciliation_changes list</action>
|
||||
</check>
|
||||
|
||||
### 7. Verify sprint-status.yaml Entry
|
||||
|
||||
<action>Read {sprint_status} file</action>
|
||||
<action>Find entry for {{story_key}}</action>
|
||||
<action>Extract current status from sprint-status.yaml</action>
|
||||
|
||||
<check if="sprint_status_yaml_status != correct_story_status">
|
||||
<output>🔧 sprint-status.yaml mismatch:
|
||||
Current: {{sprint_status_yaml_status}}
|
||||
Expected: {{correct_story_status}}
|
||||
</output>
|
||||
<action>Add to reconciliation_changes list</action>
|
||||
</check>
|
||||
|
||||
### 8. Apply Reconciliation Changes
|
||||
|
||||
<check if="reconciliation_changes is empty">
|
||||
<output>✅ Story {{story_key}}: Already accurate (0 changes needed)</output>
|
||||
<action>Return SUCCESS (no updates needed)</action>
|
||||
</check>
|
||||
|
||||
<check if="reconciliation_changes is NOT empty">
|
||||
<output>
|
||||
🔧 Story {{story_key}}: Reconciling {{count}} issues
|
||||
|
||||
**Changes to apply:**
|
||||
{{#each reconciliation_changes}}
|
||||
{{@index}}. {{change_description}}
|
||||
{{/each}}
|
||||
</output>
|
||||
|
||||
<ask>Apply these reconciliation changes? (yes/no):</ask>
|
||||
|
||||
<check if="response != 'yes'">
|
||||
<output>⏭️ Skipping reconciliation for {{story_key}}</output>
|
||||
<action>Return SUCCESS (user declined changes)</action>
|
||||
</check>
|
||||
|
||||
<substep n="8a" title="Update Acceptance Criteria">
|
||||
<action>For each AC checkbox that needs updating:</action>
|
||||
<action>Use Edit tool to update checkbox from [ ] to [x] or [~]</action>
|
||||
<action>Add note explaining why: "- [x] Item - COMPLETE: {{evidence}}"</action>
|
||||
</substep>
|
||||
|
||||
<substep n="8b" title="Update Tasks / Subtasks">
|
||||
<action>For each Task checkbox that needs updating:</action>
|
||||
<action>Use Edit tool to update checkbox</action>
|
||||
<action>Update task header if all subtasks complete: "### Task 1: ... ✅ COMPLETE"</action>
|
||||
</substep>
|
||||
|
||||
<substep n="8c" title="Update Definition of Done">
|
||||
<action>For each DoD checkbox that needs updating:</action>
|
||||
<action>Use Edit tool to update checkbox</action>
|
||||
<action>Add verification note: "- [x] Item ✅ (verified in Dev Agent Record)"</action>
|
||||
</substep>
|
||||
|
||||
<substep n="8d" title="Update Story Status">
|
||||
<check if="story status needs updating">
|
||||
<action>Use Edit tool to update status line</action>
|
||||
<action>Change from: **Status:** {{old_status}}</action>
|
||||
<action>Change to: **Status:** {{correct_story_status}}</action>
|
||||
</check>
|
||||
</substep>
|
||||
|
||||
<substep n="8e" title="Update sprint-status.yaml with status and progress">
|
||||
<check if="sprint-status.yaml needs updating">
|
||||
<action>Use Edit tool to update status entry</action>
|
||||
|
||||
<action>Count tasks from story file:
|
||||
- total_tasks = all top-level tasks
|
||||
- checked_tasks = tasks marked [x]
|
||||
- progress_pct = (checked_tasks / total_tasks) × 100
|
||||
</action>
|
||||
|
||||
<action>Update comment with progress tracking (NEW v1.3.0):
|
||||
If status == "in-progress":
|
||||
Format: {{story_key}}: in-progress # {{checked_tasks}}/{{total_tasks}} tasks ({{progress_pct}}%)
|
||||
|
||||
If status == "review":
|
||||
Format: {{story_key}}: review # {{checked_tasks}}/{{total_tasks}} tasks ({{progress_pct}}%) - awaiting review
|
||||
|
||||
If status == "done":
|
||||
Format: {{story_key}}: done # ✅ COMPLETED: {{brief_summary}}
|
||||
</action>
|
||||
|
||||
<example>
|
||||
Before: 20-8-...: ready-for-dev # Story description
|
||||
During: 20-8-...: in-progress # 3/10 tasks (30%)
|
||||
During: 20-8-...: in-progress # 7/10 tasks (70%)
|
||||
Review: 20-8-...: review # 10/10 tasks (100%) - awaiting review
|
||||
After: 20-8-...: done # ✅ COMPLETED: Component + tests + docs
|
||||
</example>
|
||||
</check>
|
||||
</substep>
|
||||
|
||||
<output>✅ Story {{story_key}}: Reconciliation complete ({{count}} changes applied)</output>
|
||||
</check>
|
||||
|
||||
### 9. Final Verification
|
||||
|
||||
<action>Re-read story file to verify changes applied correctly</action>
|
||||
<action>Calculate final completion percentages</action>
|
||||
|
||||
<output>
|
||||
📊 Story {{story_key}} - Final Status
|
||||
|
||||
**Acceptance Criteria:** {{ac_checked}}/{{ac_total}} ({{ac_pct}}%)
|
||||
**Tasks/Subtasks:** {{tasks_checked}}/{{tasks_total}} ({{tasks_pct}}%)
|
||||
**Definition of Done:** {{dod_checked}}/{{dod_total}} ({{dod_pct}}%)
|
||||
|
||||
**Story Status:** {{correct_story_status}}
|
||||
**sprint-status.yaml:** {{correct_story_status}}
|
||||
|
||||
{{#if correct_story_status == "done"}}
|
||||
✅ Story is COMPLETE and accurately reflects implementation
|
||||
{{/if}}
|
||||
|
||||
{{#if correct_story_status == "review"}}
|
||||
⚠️ Story needs review (some items incomplete)
|
||||
{{/if}}
|
||||
|
||||
{{#if correct_story_status == "in-progress"}}
|
||||
⚠️ Story has significant gaps (implementation incomplete)
|
||||
{{/if}}
|
||||
</output>
|
||||
|
||||
<action>Return SUCCESS with reconciliation summary</action>
|
||||
Agents ignore reconciliation instructions. The orchestrator:
|
||||
- Has full context of what just happened
|
||||
- Can use tools directly (Bash, Read, Edit)
|
||||
- Won't skip "boring" bookkeeping tasks
|
||||
|
||||
---
|
||||
|
||||
## Success Criteria
|
||||
## Execute These Steps
|
||||
|
||||
Story reconciliation succeeds when:
|
||||
1. ✅ All checkboxes match Dev Agent Record evidence
|
||||
2. ✅ Story status accurately reflects completion (done/review/in-progress)
|
||||
3. ✅ sprint-status.yaml entry matches story file status
|
||||
4. ✅ Completion percentages calculated and reported
|
||||
5. ✅ Changes documented in reconciliation summary
|
||||
### Step 1: Get What Was Built
|
||||
|
||||
---
|
||||
Run this command with Bash tool:
|
||||
|
||||
## Error Handling
|
||||
```bash
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "🔧 STORY RECONCILIATION: {{story_key}}"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
<check if="story file not found">
|
||||
<output>❌ Story {{story_key}}: File not found at {{story_file_path}}</output>
|
||||
<action>Return FAILED reconciliation</action>
|
||||
</check>
|
||||
# Get the commit for this story
|
||||
echo "Recent commits:"
|
||||
git log -5 --oneline | grep -i "{{story_key}}" || echo "(no commits found with story key)"
|
||||
|
||||
<check if="Dev Agent Record missing or empty">
|
||||
<output>⚠️ Story {{story_key}}: Cannot reconcile - Dev Agent Record not populated</output>
|
||||
<action>Mark as INCOMPLETE (not implemented yet)</action>
|
||||
<action>Return WARNING reconciliation</action>
|
||||
</check>
|
||||
|
||||
<check if="Edit tool fails">
|
||||
<output>❌ Story {{story_key}}: Failed to apply changes (Edit tool error)</output>
|
||||
<action>Log error details</action>
|
||||
<action>Return FAILED reconciliation</action>
|
||||
</check>
|
||||
|
||||
---
|
||||
|
||||
## Integration with batch-super-dev
|
||||
|
||||
**Insert this step:**
|
||||
- **Sequential mode:** After Step 4s-a (Process individual story), before marking completed
|
||||
- **Parallel mode:** After Step 4p-a (Spawn Task agents), after agent completes but before marking completed
|
||||
|
||||
**Flow:**
|
||||
```
|
||||
super-dev-pipeline completes → Step 4.5 (Reconcile) → Mark as completed/failed
|
||||
# Get files changed
|
||||
echo ""
|
||||
echo "Files changed in last commit:"
|
||||
git diff HEAD~1 --name-only | grep -v "__tests__" | grep -v "\.test\." | head -20
|
||||
```
|
||||
|
||||
**Benefits:**
|
||||
- Ensures all batch-processed stories have accurate status
|
||||
- Catches mismatches automatically
|
||||
- Prevents "done" stories with unchecked items
|
||||
- Maintains sprint-status.yaml accuracy
|
||||
Store the output - you'll need it for the next steps.
|
||||
|
||||
### Step 2: Read Story File
|
||||
|
||||
Use Read tool on: `docs/sprint-artifacts/{{story_key}}.md`
|
||||
|
||||
Find these sections:
|
||||
- **Tasks** (lines starting with `- [ ]` or `- [x]`)
|
||||
- **Dev Agent Record** (section with Agent Model, Implementation Date, etc.)
|
||||
|
||||
### Step 3: Check Off Completed Tasks
|
||||
|
||||
For EACH task in the Tasks section that relates to files changed:
|
||||
|
||||
Use Edit tool:
|
||||
```
|
||||
file_path: docs/sprint-artifacts/{{story_key}}.md
|
||||
old_string: "- [ ] Create the SomeComponent"
|
||||
new_string: "- [x] Create the SomeComponent"
|
||||
```
|
||||
|
||||
**Match logic:**
|
||||
- If task mentions a file that was created → check it off
|
||||
- If task mentions a service/component that now exists → check it off
|
||||
- If unsure → leave unchecked (don't over-claim)
|
||||
|
||||
### Step 4: Fill Dev Agent Record
|
||||
|
||||
Use Edit tool to replace the placeholder record:
|
||||
|
||||
```
|
||||
file_path: docs/sprint-artifacts/{{story_key}}.md
|
||||
old_string: "### Dev Agent Record
|
||||
- **Agent Model Used:** [Not set]
|
||||
- **Implementation Date:** [Not set]
|
||||
- **Files Created/Modified:** [Not set]
|
||||
- **Tests Added:** [Not set]
|
||||
- **Completion Notes:** [Not set]"
|
||||
new_string: "### Dev Agent Record
|
||||
- **Agent Model Used:** Claude Sonnet 4 (multi-agent pipeline)
|
||||
- **Implementation Date:** 2026-01-26
|
||||
- **Files Created/Modified:**
|
||||
- path/to/file1.ts
|
||||
- path/to/file2.ts
|
||||
[list all files from git diff]
|
||||
- **Tests Added:** X tests (from Inspector report)
|
||||
- **Completion Notes:** Implemented [brief summary]"
|
||||
```
|
||||
|
||||
### Step 5: Verify Updates
|
||||
|
||||
Run this command with Bash tool:
|
||||
|
||||
```bash
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "🔍 RECONCILIATION VERIFICATION"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
STORY_FILE="docs/sprint-artifacts/{{story_key}}.md"
|
||||
|
||||
# Count checked tasks
|
||||
CHECKED=$(grep -c "^- \[x\]" "$STORY_FILE" 2>/dev/null || echo "0")
|
||||
UNCHECKED=$(grep -c "^- \[ \]" "$STORY_FILE" 2>/dev/null || echo "0")
|
||||
TOTAL=$((CHECKED + UNCHECKED))
|
||||
echo "Tasks: $CHECKED/$TOTAL checked"
|
||||
|
||||
if [ "$CHECKED" -eq 0 ]; then
|
||||
echo ""
|
||||
echo "❌ BLOCKER: Zero tasks checked off"
|
||||
echo "You MUST go back to Step 3 and check off tasks"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Check Dev Agent Record filled
|
||||
if grep -q "Implementation Date: \[Not set\]" "$STORY_FILE" 2>/dev/null; then
|
||||
echo "❌ BLOCKER: Dev Agent Record not filled"
|
||||
echo "You MUST go back to Step 4 and fill it"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if grep -A 3 "### Dev Agent Record" "$STORY_FILE" | grep -q "Implementation Date: 202"; then
|
||||
echo "✅ Dev Agent Record: Filled"
|
||||
else
|
||||
echo "❌ BLOCKER: Dev Agent Record incomplete"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo ""
|
||||
echo "✅ RECONCILIATION COMPLETE"
|
||||
echo " Checked tasks: $CHECKED/$TOTAL"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
```
|
||||
|
||||
### Step 6: Update Sprint Status
|
||||
|
||||
Use Read tool: `docs/sprint-artifacts/sprint-status.yaml`
|
||||
|
||||
Find the entry for {{story_key}} and use Edit tool to update:
|
||||
|
||||
```
|
||||
old_string: "{{story_key}}: ready-for-dev"
|
||||
new_string: "{{story_key}}: done # ✅ COMPLETED 2026-01-26"
|
||||
```
|
||||
|
||||
Or if 95%+ complete but not 100%:
|
||||
```
|
||||
new_string: "{{story_key}}: review # 8/10 tasks - awaiting review"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Status Decision Logic
|
||||
|
||||
Based on verification results:
|
||||
|
||||
| Condition | Status |
|
||||
|-----------|--------|
|
||||
| 95%+ tasks checked + Dev Record filled | `done` |
|
||||
| 80-94% tasks checked | `review` |
|
||||
| <80% tasks checked | `in-progress` |
|
||||
| Dev Record not filled | `in-progress` |
|
||||
|
||||
---
|
||||
|
||||
## If Verification Fails
|
||||
|
||||
1. **DO NOT** proceed to next story
|
||||
2. **DO NOT** mark story as done
|
||||
3. **FIX** the issue using Edit tool
|
||||
4. **RE-RUN** verification command
|
||||
5. **REPEAT** until verification passes
|
||||
|
||||
This is mandatory. No shortcuts.
|
||||
|
|
|
|||
|
|
@ -93,4 +93,43 @@ When complete, provide:
|
|||
|
||||
---
|
||||
|
||||
## When Complete, Return This Format
|
||||
|
||||
```markdown
|
||||
## AGENT COMPLETE
|
||||
|
||||
**Agent:** builder
|
||||
**Story:** {{story_key}}
|
||||
**Status:** SUCCESS | FAILED
|
||||
|
||||
### Files Created
|
||||
- path/to/new/file1.ts
|
||||
- path/to/new/file2.ts
|
||||
|
||||
### Files Modified
|
||||
- path/to/existing/file.ts
|
||||
|
||||
### Tests Added
|
||||
- X test files
|
||||
- Y test cases total
|
||||
|
||||
### Implementation Summary
|
||||
Brief description of what was built and key decisions made.
|
||||
|
||||
### Known Gaps
|
||||
- Any functionality not implemented
|
||||
- Any edge cases not handled
|
||||
- NONE if all tasks complete
|
||||
|
||||
### Ready For
|
||||
Inspector validation (next phase)
|
||||
```
|
||||
|
||||
**Why this format?** The orchestrator parses this output to:
|
||||
- Verify claimed files actually exist
|
||||
- Track what was built for reconciliation
|
||||
- Route to next phase appropriately
|
||||
|
||||
---
|
||||
|
||||
**Remember:** You are the BUILDER. Build it well, but don't validate or review your own work. Other agents will do that with fresh eyes.
|
||||
|
|
|
|||
|
|
@ -20,15 +20,15 @@ You are the **FIXER** agent. Your job is to fix CRITICAL and HIGH issues from th
|
|||
- Fix security vulnerabilities immediately
|
||||
- Fix logic bugs and edge cases
|
||||
- Re-run tests after each fix
|
||||
- Update story checkboxes
|
||||
- Update sprint-status.yaml
|
||||
- Commit changes
|
||||
- Commit code changes with descriptive message
|
||||
|
||||
**DO NOT:**
|
||||
- Skip CRITICAL issues
|
||||
- Skip HIGH issues
|
||||
- Spend time on LOW issues
|
||||
- Make unnecessary changes
|
||||
- Update story checkboxes (orchestrator does this)
|
||||
- Update sprint-status.yaml (orchestrator does this)
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -79,118 +79,7 @@ low_issues: [#10, #11] # SKIP (gold-plating)
|
|||
|
||||
## After Fixing Issues
|
||||
|
||||
### 1. Update Story File (MANDATORY)
|
||||
|
||||
**THIS STEP IS MANDATORY. DO NOT SKIP.**
|
||||
|
||||
**Step 1a: Identify what was built**
|
||||
```bash
|
||||
# Get list of files changed in latest commit
|
||||
git diff HEAD~1 --name-only
|
||||
|
||||
# Get commit message
|
||||
git log -1 --pretty=%B
|
||||
```
|
||||
|
||||
**Step 1b: Read story Tasks section**
|
||||
```bash
|
||||
# Find the Tasks section in story file
|
||||
grep -A 100 "^## Tasks" docs/sprint-artifacts/{{story_key}}.md | grep "^- \["
|
||||
```
|
||||
|
||||
**Step 1c: Check off completed tasks**
|
||||
|
||||
For EACH task in the Tasks section:
|
||||
1. Read the task description
|
||||
2. Check if related files/functions exist in git diff
|
||||
3. If code for that task exists, use Edit tool to change `- [ ]` to `- [x]`
|
||||
4. Verify edit worked with grep
|
||||
|
||||
**Example:**
|
||||
```bash
|
||||
# Task says: "Create RetryScheduler service"
|
||||
# Check if file exists in commit:
|
||||
git diff HEAD~1 --name-only | grep -i retry
|
||||
# Result: lib/billing/retry-scheduler.ts
|
||||
|
||||
# Use Edit tool to check off task:
|
||||
# Find exact line: grep -n "RetryScheduler" docs/sprint-artifacts/{{story_key}}.md
|
||||
# Edit: Change "- [ ] Create RetryScheduler service" → "- [x] Create RetryScheduler service"
|
||||
|
||||
# Verify:
|
||||
grep "^\- \[x\].*RetryScheduler" docs/sprint-artifacts/{{story_key}}.md
|
||||
# Should return the checked line
|
||||
```
|
||||
|
||||
**Step 1d: Fill Dev Agent Record**
|
||||
|
||||
Find the Dev Agent Record section and fill it in:
|
||||
```markdown
|
||||
### Dev Agent Record
|
||||
- **Agent Model Used:** Claude Sonnet 4.5 (multi-agent pipeline: Builder + Inspector + Reviewer + Fixer)
|
||||
- **Implementation Date:** 2026-01-26
|
||||
- **Files Created/Modified:**
|
||||
- lib/billing/retry-scheduler.ts
|
||||
- lib/billing/payment-processor.ts
|
||||
- lib/billing/worker.ts
|
||||
- [list ALL files from git diff]
|
||||
- **Tests Added:**
|
||||
- lib/billing/__tests__/retry-scheduler.test.ts
|
||||
- lib/billing/__tests__/payment-processor.test.ts
|
||||
- lib/billing/__tests__/worker.test.ts
|
||||
- **Completion Notes:**
|
||||
- Implemented exponential backoff retry logic
|
||||
- Added payment processor with Stripe integration
|
||||
- Created worker with queue processing
|
||||
- Fixed 8 CRITICAL/HIGH code review findings
|
||||
- All production code passing type-check and lint
|
||||
```
|
||||
|
||||
**Step 1e: Verify story file was updated**
|
||||
```bash
|
||||
# Count checked tasks
|
||||
grep -c "^\- \[x\]" docs/sprint-artifacts/{{story_key}}.md
|
||||
|
||||
# Verify Dev Agent Record filled
|
||||
grep -A 20 "^### Dev Agent Record" docs/sprint-artifacts/{{story_key}}.md | grep -c "Agent Model"
|
||||
|
||||
# If count is 0, STOP and fix it. DO NOT PROCEED to commit.
|
||||
```
|
||||
|
||||
### 2. Update Sprint Status
|
||||
|
||||
**Update sprint-status.yaml:**
|
||||
```yaml
|
||||
{{story_key}}: done # was: ready-for-dev
|
||||
```
|
||||
|
||||
### 3. Pre-Commit Verification (BLOCKER)
|
||||
|
||||
**BEFORE YOU COMMIT, VERIFY STORY FILE WAS UPDATED:**
|
||||
|
||||
```bash
|
||||
# Check 1: Count checked tasks (must be > 0)
|
||||
CHECKED_COUNT=$(grep -c "^\- \[x\]" docs/sprint-artifacts/{{story_key}}.md)
|
||||
echo "Checked tasks: $CHECKED_COUNT"
|
||||
|
||||
# Check 2: Verify Dev Agent Record filled (must be 1)
|
||||
RECORD_FILLED=$(grep -A 20 "^### Dev Agent Record" docs/sprint-artifacts/{{story_key}}.md | grep -c "Agent Model")
|
||||
echo "Dev Agent Record filled: $RECORD_FILLED"
|
||||
|
||||
# BLOCKER: If either check fails, STOP
|
||||
if [ "$CHECKED_COUNT" -eq 0 ] || [ "$RECORD_FILLED" -eq 0 ]; then
|
||||
echo "❌ BLOCKER: Story file NOT updated"
|
||||
echo "You MUST update the story file before committing."
|
||||
echo "Go back to Step 1 and complete the story reconciliation."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✅ Story file verification passed"
|
||||
```
|
||||
|
||||
### 4. Commit Changes
|
||||
|
||||
**Only proceed if Step 3 verification passed:**
|
||||
### Commit Changes
|
||||
|
||||
```bash
|
||||
git add .
|
||||
|
|
@ -247,21 +136,8 @@ All tests passing, type check clean, lint clean."
|
|||
- ✅ Build: PASS
|
||||
- ✅ Tests: 48/48 passing (96% coverage)
|
||||
|
||||
**Story File Updates (MANDATORY):**
|
||||
- ✅ Tasks checked off: X/Y tasks marked complete
|
||||
- ✅ Dev Agent Record filled with files and notes
|
||||
- ✅ Verified with grep (counts > 0)
|
||||
|
||||
**Git:**
|
||||
- ✅ Commit created: a1b2c3d
|
||||
- ✅ Sprint status updated to "done"
|
||||
|
||||
**Pre-Commit Verification:**
|
||||
- ✅ Checked tasks count: X (must be > 0)
|
||||
- ✅ Dev Agent Record filled: YES (must be 1)
|
||||
- ✅ BLOCKER passed
|
||||
|
||||
**Story Status:** COMPLETE
|
||||
```
|
||||
|
||||
---
|
||||
|
|
@ -288,4 +164,47 @@ All tests passing, type check clean, lint clean."
|
|||
|
||||
---
|
||||
|
||||
## When Complete, Return This Format
|
||||
|
||||
```markdown
|
||||
## AGENT COMPLETE
|
||||
|
||||
**Agent:** fixer
|
||||
**Story:** {{story_key}}
|
||||
**Status:** SUCCESS | PARTIAL | FAILED
|
||||
|
||||
### Issues Fixed
|
||||
- **CRITICAL:** X/Y fixed
|
||||
- **HIGH:** X/Y fixed
|
||||
- **Total:** X issues resolved
|
||||
|
||||
### Fixes Applied
|
||||
1. [CRITICAL] file.ts:45 - Fixed SQL injection with parameterized query
|
||||
2. [HIGH] file.ts:89 - Added null check
|
||||
|
||||
### Files Modified
|
||||
- path/to/file1.ts
|
||||
- path/to/file2.ts
|
||||
|
||||
### Quality Checks
|
||||
- **Type Check:** PASS | FAIL
|
||||
- **Lint:** PASS | FAIL
|
||||
- **Tests:** X passing, Y failing
|
||||
|
||||
### Git Commit
|
||||
- **Hash:** abc123
|
||||
- **Message:** fix({{story_key}}): address code review findings
|
||||
|
||||
### Deferred Issues
|
||||
- MEDIUM: X issues (defer to follow-up)
|
||||
- LOW: X issues (skip as gold-plating)
|
||||
|
||||
### Ready For
|
||||
Orchestrator reconciliation (story file updates)
|
||||
```
|
||||
|
||||
**Note:** Story checkboxes and sprint-status updates are done by the orchestrator, not you.
|
||||
|
||||
---
|
||||
|
||||
**Remember:** You are the FIXER. Fix real problems, skip gold-plating, commit when done.
|
||||
|
|
|
|||
|
|
@ -150,4 +150,35 @@ Cannot proceed to code review until these are fixed.
|
|||
|
||||
---
|
||||
|
||||
## When Complete, Return This Format
|
||||
|
||||
```markdown
|
||||
## AGENT COMPLETE
|
||||
|
||||
**Agent:** inspector
|
||||
**Story:** {{story_key}}
|
||||
**Status:** PASS | FAIL
|
||||
|
||||
### Evidence
|
||||
- **Type Check:** PASS (0 errors) | FAIL (X errors)
|
||||
- **Lint:** PASS (0 warnings) | FAIL (X warnings)
|
||||
- **Build:** PASS | FAIL
|
||||
- **Tests:** X passing, Y failing, Z% coverage
|
||||
|
||||
### Files Verified
|
||||
- path/to/file1.ts ✓
|
||||
- path/to/file2.ts ✓
|
||||
- path/to/missing.ts ✗ (NOT FOUND)
|
||||
|
||||
### Failures (if FAIL status)
|
||||
1. Specific failure with file:line reference
|
||||
2. Another specific failure
|
||||
|
||||
### Ready For
|
||||
- If PASS: Reviewer (next phase)
|
||||
- If FAIL: Builder needs to fix before proceeding
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**Remember:** You are the INSPECTOR. Your job is to find the truth, not rubber-stamp the Builder's work. If something is wrong, say so with evidence.
|
||||
|
|
|
|||
|
|
@ -1,226 +0,0 @@
|
|||
# Reconciler Agent - Story File Update (MANDATORY)
|
||||
|
||||
**Role:** Update story file with implementation results
|
||||
**Step:** 10 (final - runs after Fixer completes)
|
||||
**Trust Level:** HIGH (simple, focused task)
|
||||
**Mandatory:** YES (cannot be skipped)
|
||||
|
||||
---
|
||||
|
||||
## Your Mission
|
||||
|
||||
You are the **RECONCILER** agent. Your ONLY job is to update the story file to reflect what was built.
|
||||
|
||||
🚨 **THIS IS THE MOST IMPORTANT STEP** 🚨
|
||||
|
||||
Without this step, no one knows what was built. The story file is the source of truth.
|
||||
|
||||
---
|
||||
|
||||
## What You Must Do
|
||||
|
||||
### Step 1: Read the Git Commit
|
||||
|
||||
```bash
|
||||
# Get the commit message for this story
|
||||
git log -1 --pretty=format:"%H %s %b" | head -20
|
||||
|
||||
# Get files changed
|
||||
git diff HEAD~1 --name-only | grep -v "^test/" | grep -v "__tests__"
|
||||
```
|
||||
|
||||
**Extract:**
|
||||
- Commit SHA
|
||||
- Files created/modified (production code only, exclude tests for now)
|
||||
- What was built (from commit message)
|
||||
|
||||
---
|
||||
|
||||
### Step 2: Read the Story File
|
||||
|
||||
```bash
|
||||
# Read the full story file
|
||||
cat docs/sprint-artifacts/{{story_key}}.md
|
||||
```
|
||||
|
||||
**Find:**
|
||||
- Tasks section (look for `## Tasks`)
|
||||
- Dev Agent Record section (look for `### Dev Agent Record`)
|
||||
- Current completion status
|
||||
|
||||
---
|
||||
|
||||
### Step 3: Check Off Completed Tasks
|
||||
|
||||
**For EACH task in the Tasks section:**
|
||||
|
||||
1. **Read the task description**
|
||||
2. **Check if related code exists in git diff**
|
||||
- Does the task mention a file that was created/modified?
|
||||
- Does the task mention a function/service that now exists?
|
||||
3. **If YES: Use Edit tool to check it off**
|
||||
- Change `- [ ]` to `- [x]`
|
||||
- Use exact string matching
|
||||
4. **Verify the edit worked:**
|
||||
```bash
|
||||
grep "^\- \[x\].*{{task keyword}}" docs/sprint-artifacts/{{story_key}}.md
|
||||
```
|
||||
|
||||
**Example:**
|
||||
|
||||
Task: `- [ ] Create BillingWorker service`
|
||||
|
||||
Check if it exists:
|
||||
```bash
|
||||
git diff HEAD~1 --name-only | grep -i "worker"
|
||||
# Returns: lib/billing/worker.ts
|
||||
```
|
||||
|
||||
Edit the story file:
|
||||
```typescript
|
||||
old_string: "- [ ] Create BillingWorker service"
|
||||
new_string: "- [x] Create BillingWorker service"
|
||||
```
|
||||
|
||||
Verify:
|
||||
```bash
|
||||
grep "^\- \[x\].*BillingWorker" docs/sprint-artifacts/{{story_key}}.md
|
||||
# Should return the checked line
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Step 4: Fill Dev Agent Record
|
||||
|
||||
Find the Dev Agent Record section and replace it with actual data:
|
||||
|
||||
**BEFORE:**
|
||||
```markdown
|
||||
### Dev Agent Record
|
||||
- **Agent Model Used:** [Not set]
|
||||
- **Implementation Date:** [Not set]
|
||||
- **Files Created/Modified:** [Not set]
|
||||
- **Tests Added:** [Not set]
|
||||
- **Completion Notes:** [Not set]
|
||||
```
|
||||
|
||||
**AFTER:**
|
||||
```markdown
|
||||
### Dev Agent Record
|
||||
- **Agent Model Used:** Claude Sonnet 4.5 (multi-agent: Builder + Inspector + Reviewer + Fixer + Reconciler)
|
||||
- **Implementation Date:** 2026-01-26
|
||||
- **Files Created/Modified:**
|
||||
- lib/billing/worker.ts
|
||||
- lib/billing/payment-processor.ts
|
||||
- lib/billing/retry-scheduler.ts
|
||||
- [ALL files from git diff --name-only HEAD~1]
|
||||
- **Tests Added:**
|
||||
- lib/billing/__tests__/worker.test.ts
|
||||
- lib/billing/__tests__/payment-processor.test.ts
|
||||
- lib/billing/__tests__/retry-scheduler.test.ts
|
||||
- **Completion Notes:**
|
||||
- Implemented retry logic with exponential backoff
|
||||
- Fixed 8 CRITICAL/HIGH code review findings
|
||||
- All type checks passing, lint clean
|
||||
- Tests: [status from Inspector report]
|
||||
```
|
||||
|
||||
Use the Edit tool to replace the entire Dev Agent Record section.
|
||||
|
||||
---
|
||||
|
||||
### Step 5: Verify Your Work (BLOCKER)
|
||||
|
||||
🚨 **THIS VERIFICATION IS MANDATORY. YOU MUST RUN IT.** 🚨
|
||||
|
||||
```bash
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "🔍 RECONCILIATION VERIFICATION"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
# Check 1: Count checked tasks
|
||||
CHECKED_COUNT=$(grep -c "^\- \[x\]" docs/sprint-artifacts/{{story_key}}.md)
|
||||
echo "Checked tasks: $CHECKED_COUNT"
|
||||
|
||||
if [ "$CHECKED_COUNT" -eq 0 ]; then
|
||||
echo ""
|
||||
echo "❌ RECONCILIATION FAILED"
|
||||
echo "Story file has ZERO checked tasks."
|
||||
echo "You MUST go back to Step 3 and check off tasks."
|
||||
echo ""
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Check 2: Verify Dev Agent Record filled
|
||||
RECORD_FILLED=$(grep -A 20 "^### Dev Agent Record" docs/sprint-artifacts/{{story_key}}.md | grep -c "Claude Sonnet")
|
||||
echo "Dev Agent Record filled: $RECORD_FILLED"
|
||||
|
||||
if [ "$RECORD_FILLED" -eq 0 ]; then
|
||||
echo ""
|
||||
echo "❌ RECONCILIATION FAILED"
|
||||
echo "Dev Agent Record NOT filled."
|
||||
echo "You MUST go back to Step 4 and fill it in."
|
||||
echo ""
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo ""
|
||||
echo "✅ RECONCILIATION SUCCESSFUL"
|
||||
echo " - Checked tasks: $CHECKED_COUNT"
|
||||
echo " - Dev Agent Record: FILLED"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
```
|
||||
|
||||
**If verification fails:**
|
||||
- STOP immediately
|
||||
- Fix the issue
|
||||
- Re-run verification
|
||||
- DO NOT report "COMPLETE" until verification passes
|
||||
|
||||
**If verification passes:**
|
||||
- Report success with task count
|
||||
- Story is now officially complete
|
||||
|
||||
---
|
||||
|
||||
## Output Requirements
|
||||
|
||||
**Provide Reconciliation Summary:**
|
||||
|
||||
```markdown
|
||||
## Reconciliation Complete
|
||||
|
||||
**Story File Updated:**
|
||||
- ✅ Tasks checked: X/Y tasks marked complete
|
||||
- ✅ Dev Agent Record filled with implementation details
|
||||
- ✅ Verification passed
|
||||
|
||||
**What Was Built:**
|
||||
- File 1: lib/billing/worker.ts (BillingWorker service)
|
||||
- File 2: lib/billing/payment-processor.ts (Payment processing)
|
||||
- File 3: lib/billing/retry-scheduler.ts (Retry scheduling)
|
||||
- [List ALL production files from git diff]
|
||||
|
||||
**Tests:**
|
||||
- X tests added
|
||||
- Y tests passing
|
||||
- Coverage: Z%
|
||||
|
||||
**Story Status:** READY FOR COMPLETION
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Remember
|
||||
|
||||
🚨 **Your job is RECONCILIATION, not implementation** 🚨
|
||||
|
||||
- Don't write code
|
||||
- Don't fix bugs
|
||||
- Don't run tests
|
||||
- ONLY update the story file
|
||||
- ONLY verify it worked
|
||||
|
||||
If you do this right, the user will know EXACTLY what was built and can mark the story done with confidence.
|
||||
|
||||
**This is the last step. Make it count.**
|
||||
|
|
@ -187,4 +187,37 @@ Before completing review, check:
|
|||
|
||||
---
|
||||
|
||||
## When Complete, Return This Format
|
||||
|
||||
```markdown
|
||||
## AGENT COMPLETE
|
||||
|
||||
**Agent:** reviewer
|
||||
**Story:** {{story_key}}
|
||||
**Status:** ISSUES_FOUND | CLEAN
|
||||
|
||||
### Issue Summary
|
||||
- **CRITICAL:** X issues (security, data loss)
|
||||
- **HIGH:** X issues (production bugs)
|
||||
- **MEDIUM:** X issues (tech debt)
|
||||
- **LOW:** X issues (nice-to-have)
|
||||
- **TOTAL:** X issues
|
||||
|
||||
### Must Fix (CRITICAL + HIGH)
|
||||
1. [CRITICAL] file.ts:45 - SQL injection in user query
|
||||
2. [HIGH] file.ts:89 - Missing null check causes crash
|
||||
|
||||
### Should Fix (MEDIUM)
|
||||
1. file.ts:123 - No error handling for API call
|
||||
|
||||
### Files Reviewed
|
||||
- path/to/file1.ts ✓
|
||||
- path/to/file2.ts ✓
|
||||
|
||||
### Ready For
|
||||
Fixer agent to address CRITICAL and HIGH issues
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**Remember:** You are the ADVERSARIAL REVIEWER. Your success is measured by finding legitimate issues. Don't be nice - be thorough.
|
||||
|
|
|
|||
|
|
@ -1,16 +1,19 @@
|
|||
# Super-Dev-Pipeline v2.0 - Multi-Agent Architecture
|
||||
# Super-Dev-Pipeline v2.1 - Multi-Agent Architecture
|
||||
|
||||
**Version:** 2.0.0
|
||||
**Version:** 2.1.0
|
||||
**Architecture:** GSDMAD (GSD + BMAD)
|
||||
**Philosophy:** Trust but verify, separation of concerns
|
||||
**Philosophy:** Agents do creative work, orchestrator does bookkeeping
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
This workflow implements a story using **4 independent agents** with external validation at each phase.
|
||||
This workflow implements a story using **4 independent agents** with orchestrator-driven reconciliation.
|
||||
|
||||
**Key Innovation:** Each agent has single responsibility and fresh context. No agent validates its own work.
|
||||
**Key Innovation:**
|
||||
- Each agent has single responsibility and fresh context
|
||||
- No agent validates its own work
|
||||
- **Orchestrator does bookkeeping** (story file updates, verification) - not agents
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -22,44 +25,45 @@ This workflow implements a story using **4 independent agents** with external va
|
|||
│ - Loads story │
|
||||
│ - Spawns agents sequentially │
|
||||
│ - Verifies each phase │
|
||||
│ - DOES RECONCILIATION DIRECTLY (not via agent) │
|
||||
│ - Final quality gate │
|
||||
└─────────────────────────────────────────────────────────────┘
|
||||
│
|
||||
├──> Phase 1: Builder (Steps 1-4)
|
||||
├──> Phase 1: Builder (Steps 1-4) [AGENT]
|
||||
│ - Load story, analyze gaps
|
||||
│ - Write tests (TDD)
|
||||
│ - Implement code
|
||||
│ - Report what was built (NO VALIDATION)
|
||||
│
|
||||
├──> Phase 2: Inspector (Steps 5-6)
|
||||
├──> Phase 2: Inspector (Steps 5-6) [AGENT]
|
||||
│ - Fresh context, no Builder knowledge
|
||||
│ - Verify files exist
|
||||
│ - Run tests independently
|
||||
│ - Run quality checks
|
||||
│ - PASS or FAIL verdict
|
||||
│
|
||||
├──> Phase 3: Reviewer (Step 7)
|
||||
├──> Phase 3: Reviewer (Step 7) [AGENT]
|
||||
│ - Fresh context, adversarial stance
|
||||
│ - Find security vulnerabilities
|
||||
│ - Find performance problems
|
||||
│ - Find logic bugs
|
||||
│ - Report issues with severity
|
||||
│
|
||||
├──> Phase 4: Fixer (Steps 8-9)
|
||||
├──> Phase 4: Fixer (Steps 8-9) [AGENT]
|
||||
│ - Fix CRITICAL issues (all)
|
||||
│ - Fix HIGH issues (all)
|
||||
│ - Fix MEDIUM issues (if time)
|
||||
│ - Skip LOW issues (gold-plating)
|
||||
│ - Commit code changes
|
||||
│
|
||||
├──> Phase 5: Reconciler (Step 10) 🚨 MANDATORY
|
||||
│ - Read git commit to see what was built
|
||||
├──> Phase 5: Reconciliation (Step 10) [ORCHESTRATOR] 🔧
|
||||
│ - Orchestrator uses Bash/Read/Edit tools directly
|
||||
│ - Check off completed tasks in story file
|
||||
│ - Fill Dev Agent Record with details
|
||||
│ - VERIFY updates with bash commands
|
||||
│ - BLOCKER: Exit 1 if verification fails
|
||||
│ - Verify updates with bash commands
|
||||
│ - BLOCKER if verification fails
|
||||
│
|
||||
└──> Final Verification (Main)
|
||||
└──> Final Verification [ORCHESTRATOR]
|
||||
- Check git commits exist
|
||||
- Check story checkboxes updated (count > 0)
|
||||
- Check Dev Agent Record filled
|
||||
|
|
@ -190,52 +194,89 @@ Task({
|
|||
|
||||
**Wait for Fixer to complete.**
|
||||
|
||||
### Phase 5: Spawn Reconciler (MANDATORY)
|
||||
### Phase 5: Orchestrator Reconciliation (MANDATORY)
|
||||
|
||||
🚨 **THIS PHASE IS MANDATORY. ALWAYS RUN. CANNOT BE SKIPPED.** 🚨
|
||||
🚨 **THIS PHASE IS MANDATORY. ORCHESTRATOR DOES THIS DIRECTLY. NO AGENT SPAWN.** 🚨
|
||||
|
||||
```javascript
|
||||
Task({
|
||||
subagent_type: "general-purpose",
|
||||
description: "Reconcile story {{story_key}}",
|
||||
prompt: `
|
||||
You are the RECONCILER agent for story {{story_key}}.
|
||||
**Why orchestrator, not agent?** Agents ignore instructions. The orchestrator has the context
|
||||
and can use tools directly. This is bookkeeping work, not creative work.
|
||||
|
||||
Load and execute: {agents_path}/reconciler.md
|
||||
**YOU (the orchestrator) must execute these commands directly:**
|
||||
|
||||
Story file: {{story_file}}
|
||||
Story key: {{story_key}}
|
||||
**Step 5.1: Get what was built**
|
||||
```bash
|
||||
# Get commit for this story
|
||||
COMMIT_INFO=$(git log -5 --oneline | grep "{{story_key}}" | head -1)
|
||||
echo "Commit: $COMMIT_INFO"
|
||||
|
||||
Complete Step 10 - Story Reconciliation:
|
||||
|
||||
Your ONLY job:
|
||||
1. Read git commit to see what was built
|
||||
2. Check off completed tasks in story file (Edit tool)
|
||||
3. Fill Dev Agent Record with files/dates/notes
|
||||
4. Verify updates worked (bash grep commands)
|
||||
5. Exit 1 if verification fails
|
||||
|
||||
DO NOT:
|
||||
- Write code
|
||||
- Fix bugs
|
||||
- Run tests
|
||||
- Do anything except update the story file
|
||||
|
||||
This is the LAST step. The story cannot be marked complete
|
||||
without your verification passing.
|
||||
|
||||
Output: Reconciliation summary with checked task count.
|
||||
`
|
||||
});
|
||||
# Get files changed (production code only)
|
||||
FILES_CHANGED=$(git diff HEAD~1 --name-only | grep -v "__tests__" | grep -v "\.test\." | grep -v "\.spec\.")
|
||||
echo "Files changed:"
|
||||
echo "$FILES_CHANGED"
|
||||
```
|
||||
|
||||
**Wait for Reconciler to complete. Verification MUST pass.**
|
||||
**Step 5.2: Read story file tasks**
|
||||
Use Read tool: `{{story_file}}`
|
||||
|
||||
**If Reconciler verification fails (exit 1):**
|
||||
- DO NOT proceed
|
||||
- DO NOT mark story complete
|
||||
- Fix the reconciliation immediately
|
||||
- Re-run Reconciler until it passes
|
||||
Find the Tasks section and identify which tasks relate to the files changed.
|
||||
|
||||
**Step 5.3: Check off completed tasks**
|
||||
Use Edit tool for EACH task that was completed:
|
||||
```
|
||||
old_string: "- [ ] Task description here"
|
||||
new_string: "- [x] Task description here"
|
||||
```
|
||||
|
||||
**Step 5.4: Fill Dev Agent Record**
|
||||
Use Edit tool to update the Dev Agent Record section:
|
||||
```
|
||||
old_string: "### Dev Agent Record
|
||||
- **Agent Model Used:** [Not set]
|
||||
- **Implementation Date:** [Not set]
|
||||
- **Files Created/Modified:** [Not set]
|
||||
- **Tests Added:** [Not set]
|
||||
- **Completion Notes:** [Not set]"
|
||||
|
||||
new_string: "### Dev Agent Record
|
||||
- **Agent Model Used:** Claude Sonnet 4 (multi-agent: Builder + Inspector + Reviewer + Fixer)
|
||||
- **Implementation Date:** {{date}}
|
||||
- **Files Created/Modified:**
|
||||
{{#each files_changed}}
|
||||
- {{this}}
|
||||
{{/each}}
|
||||
- **Tests Added:** [count from Inspector report]
|
||||
- **Completion Notes:** [brief summary of what was implemented]"
|
||||
```
|
||||
|
||||
**Step 5.5: Verify updates (BLOCKER)**
|
||||
```bash
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "🔍 RECONCILIATION VERIFICATION"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
# Count checked tasks
|
||||
CHECKED=$(grep -c "^- \[x\]" {{story_file}})
|
||||
echo "Checked tasks: $CHECKED"
|
||||
|
||||
if [ "$CHECKED" -eq 0 ]; then
|
||||
echo "❌ BLOCKER: Zero checked tasks"
|
||||
echo "Go back to Step 5.3 and check off tasks"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Verify Dev Agent Record
|
||||
RECORD=$(grep -A 5 "### Dev Agent Record" {{story_file}} | grep -c "Implementation Date:")
|
||||
if [ "$RECORD" -eq 0 ]; then
|
||||
echo "❌ BLOCKER: Dev Agent Record not filled"
|
||||
echo "Go back to Step 5.4 and fill it"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✅ Reconciliation verified: $CHECKED tasks checked"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
```
|
||||
|
||||
**If verification fails:** DO NOT proceed. Fix immediately using Edit tool, then re-verify.
|
||||
|
||||
---
|
||||
|
||||
|
|
|
|||
|
|
@ -67,15 +67,7 @@ agents:
|
|||
trust_level: "medium" # Incentive to minimize work
|
||||
timeout: 2400 # 40 minutes
|
||||
|
||||
reconciler:
|
||||
description: "Story reconciliation - MANDATORY story file updates"
|
||||
steps: [10]
|
||||
subagent_type: "general-purpose"
|
||||
prompt_file: "{agents_path}/reconciler.md"
|
||||
trust_level: "high" # Simple, focused task
|
||||
timeout: 600 # 10 minutes
|
||||
mandatory: true # Cannot be skipped
|
||||
runs_after: "fixer"
|
||||
# Reconciliation: orchestrator does this directly (see workflow.md Phase 5)
|
||||
|
||||
# Complexity level (determines which steps to execute)
|
||||
complexity_level: "standard" # micro | standard | complex
|
||||
|
|
|
|||
Loading…
Reference in New Issue